PANNs (models_onnx)

.gitattributes

@@ -34,3 +34,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 PANNs.[[:space:]]Large-Scale[[:space:]]Pretrained[[:space:]]Audio[[:space:]]Neural[[:space:]]Networks[[:space:]]for[[:space:]]Audio[[:space:]]Pattern[[:space:]]Recognition.pdf filter=lfs diff=lfs merge=lfs -text
+models/onnx/ailia-models/code/output.png filter=lfs diff=lfs merge=lfs -text
+models/onnx/ailia-models/code/R9_ZSCveAHg_7s.wav filter=lfs diff=lfs merge=lfs -text

models/onnx/ailia-models/audio_tagging.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db1ec74b56aadcc9bc4ea6864e6514101f13b05f6bcc1df7fee508bcc2cdbe48
+size 327324443

models/onnx/ailia-models/audio_tagging.onnx.prototxt

@@ -0,0 +1,1565 @@
+ir_version: 4
+producer_name: "pytorch"
+producer_version: "1.11.0"
+model_version: 0
+graph {
+  name: "torch-jit-export"
+  node {
+    input: "input.1"
+    output: "onnx::Pad_85"
+    name: "Unsqueeze_0"
+    op_type: "Unsqueeze"
+    attribute {
+      name: "axes"
+      ints: 1
+      type: INTS
+    }
+  }
+  node {
+    input: "onnx::Pad_85"
+    output: "input"
+    name: "Pad_1"
+    op_type: "Pad"
+    attribute {
+      name: "mode"
+      s: "reflect"
+      type: STRING
+    }
+    attribute {
+      name: "pads"
+      ints: 0
+      ints: 0
+      ints: 512
+      ints: 0
+      ints: 0
+      ints: 512
+      type: INTS
+    }
+  }
+  node {
+    input: "input"
+    input: "spectrogram_extractor.stft.conv_real.weight"
+    output: "onnx::Unsqueeze_87"
+    name: "Conv_2"
+    op_type: "Conv"
+    attribute {
+      name: "dilations"
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "group"
+      i: 1
+      type: INT
+    }
+    attribute {
+      name: "kernel_shape"
+      ints: 1024
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 0
+      ints: 0
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 320
+      type: INTS
+    }
+  }
+  node {
+    input: "input"
+    input: "spectrogram_extractor.stft.conv_imag.weight"
+    output: "onnx::Unsqueeze_88"
+    name: "Conv_3"
+    op_type: "Conv"
+    attribute {
+      name: "dilations"
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "group"
+      i: 1
+      type: INT
+    }
+    attribute {
+      name: "kernel_shape"
+      ints: 1024
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 0
+      ints: 0
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 320
+      type: INTS
+    }
+  }
+  node {
+    input: "onnx::Unsqueeze_87"
+    output: "onnx::Transpose_89"
+    name: "Unsqueeze_4"
+    op_type: "Unsqueeze"
+    attribute {
+      name: "axes"
+      ints: 1
+      type: INTS
+    }
+  }
+  node {
+    input: "onnx::Transpose_89"
+    output: "real"
+    name: "Transpose_5"
+    op_type: "Transpose"
+    attribute {
+      name: "perm"
+      ints: 0
+      ints: 1
+      ints: 3
+      ints: 2
+      type: INTS
+    }
+  }
+  node {
+    input: "onnx::Unsqueeze_88"
+    output: "onnx::Transpose_91"
+    name: "Unsqueeze_6"
+    op_type: "Unsqueeze"
+    attribute {
+      name: "axes"
+      ints: 1
+      type: INTS
+    }
+  }
+  node {
+    input: "onnx::Transpose_91"
+    output: "imag"
+    name: "Transpose_7"
+    op_type: "Transpose"
+    attribute {
+      name: "perm"
+      ints: 0
+      ints: 1
+      ints: 3
+      ints: 2
+      type: INTS
+    }
+  }
+  node {
+    input: "real"
+    input: "onnx::Pow_204"
+    output: "onnx::Add_95"
+    name: "Pow_8"
+    op_type: "Pow"
+  }
+  node {
+    input: "imag"
+    input: "onnx::Pow_205"
+    output: "onnx::Add_98"
+    name: "Pow_9"
+    op_type: "Pow"
+  }
+  node {
+    input: "onnx::Add_95"
+    input: "onnx::Add_98"
+    output: "onnx::MatMul_99"
+    name: "Add_10"
+    op_type: "Add"
+  }
+  node {
+    input: "onnx::MatMul_99"
+    input: "logmel_extractor.melW"
+    output: "mel_spectrogram"
+    name: "MatMul_11"
+    op_type: "MatMul"
+  }
+  node {
+    input: "mel_spectrogram"
+    output: "onnx::Log_101"
+    name: "Clip_12"
+    op_type: "Clip"
+    attribute {
+      name: "max"
+      f: inf
+      type: FLOAT
+    }
+    attribute {
+      name: "min"
+      f: 1.000000013351432e-10
+      type: FLOAT
+    }
+  }
+  node {
+    input: "onnx::Log_101"
+    output: "onnx::Div_102"
+    name: "Log_13"
+    op_type: "Log"
+  }
+  node {
+    output: "onnx::Div_103"
+    name: "Constant_14"
+    op_type: "Constant"
+    attribute {
+      name: "value"
+      t {
+        dims: 1
+        data_type: 1
+      }
+      type: TENSOR
+    }
+  }
+  node {
+    input: "onnx::Div_102"
+    input: "onnx::Div_103"
+    output: "onnx::Mul_104"
+    name: "Div_15"
+    op_type: "Div"
+  }
+  node {
+    output: "onnx::Mul_105"
+    name: "Constant_16"
+    op_type: "Constant"
+    attribute {
+      name: "value"
+      t {
+        data_type: 1
+      }
+      type: TENSOR
+    }
+  }
+  node {
+    input: "onnx::Mul_104"
+    input: "onnx::Mul_105"
+    output: "onnx::Sub_106"
+    name: "Mul_17"
+    op_type: "Mul"
+  }
+  node {
+    output: "onnx::Sub_107"
+    name: "Constant_18"
+    op_type: "Constant"
+    attribute {
+      name: "value"
+      t {
+        data_type: 1
+      }
+      type: TENSOR
+    }
+  }
+  node {
+    input: "onnx::Sub_106"
+    input: "onnx::Sub_107"
+    output: "onnx::Transpose_108"
+    name: "Sub_19"
+    op_type: "Sub"
+  }
+  node {
+    input: "onnx::Transpose_108"
+    output: "input.4"
+    name: "Transpose_20"
+    op_type: "Transpose"
+    attribute {
+      name: "perm"
+      ints: 0
+      ints: 3
+      ints: 2
+      ints: 1
+      type: INTS
+    }
+  }
+  node {
+    input: "input.4"
+    input: "bn0.weight"
+    input: "bn0.bias"
+    input: "bn0.running_mean"
+    input: "bn0.running_var"
+    output: "onnx::Transpose_110"
+    name: "BatchNormalization_21"
+    op_type: "BatchNormalization"
+    attribute {
+      name: "epsilon"
+      f: 9.999999747378752e-06
+      type: FLOAT
+    }
+    attribute {
+      name: "momentum"
+      f: 0.8999999761581421
+      type: FLOAT
+    }
+  }
+  node {
+    input: "onnx::Transpose_110"
+    output: "input.8"
+    name: "Transpose_22"
+    op_type: "Transpose"
+    attribute {
+      name: "perm"
+      ints: 0
+      ints: 3
+      ints: 2
+      ints: 1
+      type: INTS
+    }
+  }
+  node {
+    input: "input.8"
+    input: "onnx::Conv_169"
+    input: "onnx::Conv_170"
+    output: "onnx::Relu_168"
+    name: "Conv_23"
+    op_type: "Conv"
+    attribute {
+      name: "dilations"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "group"
+      i: 1
+      type: INT
+    }
+    attribute {
+      name: "kernel_shape"
+      ints: 3
+      ints: 3
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 1
+      ints: 1
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+  }
+  node {
+    input: "onnx::Relu_168"
+    output: "onnx::Conv_114"
+    name: "Relu_24"
+    op_type: "Relu"
+  }
+  node {
+    input: "onnx::Conv_114"
+    input: "onnx::Conv_172"
+    input: "onnx::Conv_173"
+    output: "onnx::Relu_171"
+    name: "Conv_25"
+    op_type: "Conv"
+    attribute {
+      name: "dilations"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "group"
+      i: 1
+      type: INT
+    }
+    attribute {
+      name: "kernel_shape"
+      ints: 3
+      ints: 3
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 1
+      ints: 1
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+  }
+  node {
+    input: "onnx::Relu_171"
+    output: "onnx::Pad_117"
+    name: "Relu_26"
+    op_type: "Relu"
+  }
+  node {
+    input: "onnx::Pad_117"
+    output: "onnx::AveragePool_118"
+    name: "Pad_27"
+    op_type: "Pad"
+    attribute {
+      name: "mode"
+      s: "constant"
+      type: STRING
+    }
+    attribute {
+      name: "pads"
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      type: INTS
+    }
+    attribute {
+      name: "value"
+      f: 0.0
+      type: FLOAT
+    }
+  }
+  node {
+    input: "onnx::AveragePool_118"
+    output: "x"
+    name: "AveragePool_28"
+    op_type: "AveragePool"
+    attribute {
+      name: "kernel_shape"
+      ints: 2
+      ints: 2
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 2
+      ints: 2
+      type: INTS
+    }
+  }
+  node {
+    input: "x"
+    input: "onnx::Conv_175"
+    input: "onnx::Conv_176"
+    output: "onnx::Relu_174"
+    name: "Conv_29"
+    op_type: "Conv"
+    attribute {
+      name: "dilations"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "group"
+      i: 1
+      type: INT
+    }
+    attribute {
+      name: "kernel_shape"
+      ints: 3
+      ints: 3
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 1
+      ints: 1
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+  }
+  node {
+    input: "onnx::Relu_174"
+    output: "onnx::Conv_122"
+    name: "Relu_30"
+    op_type: "Relu"
+  }
+  node {
+    input: "onnx::Conv_122"
+    input: "onnx::Conv_178"
+    input: "onnx::Conv_179"
+    output: "onnx::Relu_177"
+    name: "Conv_31"
+    op_type: "Conv"
+    attribute {
+      name: "dilations"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "group"
+      i: 1
+      type: INT
+    }
+    attribute {
+      name: "kernel_shape"
+      ints: 3
+      ints: 3
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 1
+      ints: 1
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+  }
+  node {
+    input: "onnx::Relu_177"
+    output: "onnx::Pad_125"
+    name: "Relu_32"
+    op_type: "Relu"
+  }
+  node {
+    input: "onnx::Pad_125"
+    output: "onnx::AveragePool_126"
+    name: "Pad_33"
+    op_type: "Pad"
+    attribute {
+      name: "mode"
+      s: "constant"
+      type: STRING
+    }
+    attribute {
+      name: "pads"
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      type: INTS
+    }
+    attribute {
+      name: "value"
+      f: 0.0
+      type: FLOAT
+    }
+  }
+  node {
+    input: "onnx::AveragePool_126"
+    output: "x.3"
+    name: "AveragePool_34"
+    op_type: "AveragePool"
+    attribute {
+      name: "kernel_shape"
+      ints: 2
+      ints: 2
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 2
+      ints: 2
+      type: INTS
+    }
+  }
+  node {
+    input: "x.3"
+    input: "onnx::Conv_181"
+    input: "onnx::Conv_182"
+    output: "onnx::Relu_180"
+    name: "Conv_35"
+    op_type: "Conv"
+    attribute {
+      name: "dilations"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "group"
+      i: 1
+      type: INT
+    }
+    attribute {
+      name: "kernel_shape"
+      ints: 3
+      ints: 3
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 1
+      ints: 1
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+  }
+  node {
+    input: "onnx::Relu_180"
+    output: "onnx::Conv_130"
+    name: "Relu_36"
+    op_type: "Relu"
+  }
+  node {
+    input: "onnx::Conv_130"
+    input: "onnx::Conv_184"
+    input: "onnx::Conv_185"
+    output: "onnx::Relu_183"
+    name: "Conv_37"
+    op_type: "Conv"
+    attribute {
+      name: "dilations"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "group"
+      i: 1
+      type: INT
+    }
+    attribute {
+      name: "kernel_shape"
+      ints: 3
+      ints: 3
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 1
+      ints: 1
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+  }
+  node {
+    input: "onnx::Relu_183"
+    output: "onnx::Pad_133"
+    name: "Relu_38"
+    op_type: "Relu"
+  }
+  node {
+    input: "onnx::Pad_133"
+    output: "onnx::AveragePool_134"
+    name: "Pad_39"
+    op_type: "Pad"
+    attribute {
+      name: "mode"
+      s: "constant"
+      type: STRING
+    }
+    attribute {
+      name: "pads"
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      type: INTS
+    }
+    attribute {
+      name: "value"
+      f: 0.0
+      type: FLOAT
+    }
+  }
+  node {
+    input: "onnx::AveragePool_134"
+    output: "x.7"
+    name: "AveragePool_40"
+    op_type: "AveragePool"
+    attribute {
+      name: "kernel_shape"
+      ints: 2
+      ints: 2
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 2
+      ints: 2
+      type: INTS
+    }
+  }
+  node {
+    input: "x.7"
+    input: "onnx::Conv_187"
+    input: "onnx::Conv_188"
+    output: "onnx::Relu_186"
+    name: "Conv_41"
+    op_type: "Conv"
+    attribute {
+      name: "dilations"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "group"
+      i: 1
+      type: INT
+    }
+    attribute {
+      name: "kernel_shape"
+      ints: 3
+      ints: 3
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 1
+      ints: 1
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+  }
+  node {
+    input: "onnx::Relu_186"
+    output: "onnx::Conv_138"
+    name: "Relu_42"
+    op_type: "Relu"
+  }
+  node {
+    input: "onnx::Conv_138"
+    input: "onnx::Conv_190"
+    input: "onnx::Conv_191"
+    output: "onnx::Relu_189"
+    name: "Conv_43"
+    op_type: "Conv"
+    attribute {
+      name: "dilations"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "group"
+      i: 1
+      type: INT
+    }
+    attribute {
+      name: "kernel_shape"
+      ints: 3
+      ints: 3
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 1
+      ints: 1
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+  }
+  node {
+    input: "onnx::Relu_189"
+    output: "onnx::Pad_141"
+    name: "Relu_44"
+    op_type: "Relu"
+  }
+  node {
+    input: "onnx::Pad_141"
+    output: "onnx::AveragePool_142"
+    name: "Pad_45"
+    op_type: "Pad"
+    attribute {
+      name: "mode"
+      s: "constant"
+      type: STRING
+    }
+    attribute {
+      name: "pads"
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      type: INTS
+    }
+    attribute {
+      name: "value"
+      f: 0.0
+      type: FLOAT
+    }
+  }
+  node {
+    input: "onnx::AveragePool_142"
+    output: "x.11"
+    name: "AveragePool_46"
+    op_type: "AveragePool"
+    attribute {
+      name: "kernel_shape"
+      ints: 2
+      ints: 2
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 2
+      ints: 2
+      type: INTS
+    }
+  }
+  node {
+    input: "x.11"
+    input: "onnx::Conv_193"
+    input: "onnx::Conv_194"
+    output: "onnx::Relu_192"
+    name: "Conv_47"
+    op_type: "Conv"
+    attribute {
+      name: "dilations"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "group"
+      i: 1
+      type: INT
+    }
+    attribute {
+      name: "kernel_shape"
+      ints: 3
+      ints: 3
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 1
+      ints: 1
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+  }
+  node {
+    input: "onnx::Relu_192"
+    output: "onnx::Conv_146"
+    name: "Relu_48"
+    op_type: "Relu"
+  }
+  node {
+    input: "onnx::Conv_146"
+    input: "onnx::Conv_196"
+    input: "onnx::Conv_197"
+    output: "onnx::Relu_195"
+    name: "Conv_49"
+    op_type: "Conv"
+    attribute {
+      name: "dilations"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "group"
+      i: 1
+      type: INT
+    }
+    attribute {
+      name: "kernel_shape"
+      ints: 3
+      ints: 3
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 1
+      ints: 1
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+  }
+  node {
+    input: "onnx::Relu_195"
+    output: "onnx::Pad_149"
+    name: "Relu_50"
+    op_type: "Relu"
+  }
+  node {
+    input: "onnx::Pad_149"
+    output: "onnx::AveragePool_150"
+    name: "Pad_51"
+    op_type: "Pad"
+    attribute {
+      name: "mode"
+      s: "constant"
+      type: STRING
+    }
+    attribute {
+      name: "pads"
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      type: INTS
+    }
+    attribute {
+      name: "value"
+      f: 0.0
+      type: FLOAT
+    }
+  }
+  node {
+    input: "onnx::AveragePool_150"
+    output: "x.15"
+    name: "AveragePool_52"
+    op_type: "AveragePool"
+    attribute {
+      name: "kernel_shape"
+      ints: 2
+      ints: 2
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 2
+      ints: 2
+      type: INTS
+    }
+  }
+  node {
+    input: "x.15"
+    input: "onnx::Conv_199"
+    input: "onnx::Conv_200"
+    output: "onnx::Relu_198"
+    name: "Conv_53"
+    op_type: "Conv"
+    attribute {
+      name: "dilations"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "group"
+      i: 1
+      type: INT
+    }
+    attribute {
+      name: "kernel_shape"
+      ints: 3
+      ints: 3
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 1
+      ints: 1
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+  }
+  node {
+    input: "onnx::Relu_198"
+    output: "onnx::Conv_154"
+    name: "Relu_54"
+    op_type: "Relu"
+  }
+  node {
+    input: "onnx::Conv_154"
+    input: "onnx::Conv_202"
+    input: "onnx::Conv_203"
+    output: "onnx::Relu_201"
+    name: "Conv_55"
+    op_type: "Conv"
+    attribute {
+      name: "dilations"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "group"
+      i: 1
+      type: INT
+    }
+    attribute {
+      name: "kernel_shape"
+      ints: 3
+      ints: 3
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 1
+      ints: 1
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+  }
+  node {
+    input: "onnx::Relu_201"
+    output: "onnx::Pad_157"
+    name: "Relu_56"
+    op_type: "Relu"
+  }
+  node {
+    input: "onnx::Pad_157"
+    output: "onnx::AveragePool_158"
+    name: "Pad_57"
+    op_type: "Pad"
+    attribute {
+      name: "mode"
+      s: "constant"
+      type: STRING
+    }
+    attribute {
+      name: "pads"
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      type: INTS
+    }
+    attribute {
+      name: "value"
+      f: 0.0
+      type: FLOAT
+    }
+  }
+  node {
+    input: "onnx::AveragePool_158"
+    output: "x.19"
+    name: "AveragePool_58"
+    op_type: "AveragePool"
+    attribute {
+      name: "kernel_shape"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+  }
+  node {
+    input: "x.19"
+    output: "onnx::ReduceMax_160"
+    name: "ReduceMean_59"
+    op_type: "ReduceMean"
+    attribute {
+      name: "axes"
+      ints: 3
+      type: INTS
+    }
+    attribute {
+      name: "keepdims"
+      i: 0
+      type: INT
+    }
+  }
+  node {
+    input: "onnx::ReduceMax_160"
+    output: "onnx::Add_161"
+    name: "ReduceMax_60"
+    op_type: "ReduceMax"
+    attribute {
+      name: "axes"
+      ints: 2
+      type: INTS
+    }
+    attribute {
+      name: "keepdims"
+      i: 0
+      type: INT
+    }
+  }
+  node {
+    input: "onnx::ReduceMax_160"
+    output: "onnx::Add_162"
+    name: "ReduceMean_61"
+    op_type: "ReduceMean"
+    attribute {
+      name: "axes"
+      ints: 2
+      type: INTS
+    }
+    attribute {
+      name: "keepdims"
+      i: 0
+      type: INT
+    }
+  }
+  node {
+    input: "onnx::Add_161"
+    input: "onnx::Add_162"
+    output: "x.23"
+    name: "Add_62"
+    op_type: "Add"
+  }
+  node {
+    input: "x.23"
+    input: "fc1.weight"
+    input: "fc1.bias"
+    output: "onnx::Relu_164"
+    name: "Gemm_63"
+    op_type: "Gemm"
+    attribute {
+      name: "alpha"
+      f: 1.0
+      type: FLOAT
+    }
+    attribute {
+      name: "beta"
+      f: 1.0
+      type: FLOAT
+    }
+    attribute {
+      name: "transB"
+      i: 1
+      type: INT
+    }
+  }
+  node {
+    input: "onnx::Relu_164"
+    output: "onnx::Gemm_165"
+    name: "Relu_64"
+    op_type: "Relu"
+  }
+  node {
+    input: "onnx::Gemm_165"
+    input: "fc_audioset.weight"
+    input: "fc_audioset.bias"
+    output: "onnx::Sigmoid_166"
+    name: "Gemm_65"
+    op_type: "Gemm"
+    attribute {
+      name: "alpha"
+      f: 1.0
+      type: FLOAT
+    }
+    attribute {
+      name: "beta"
+      f: 1.0
+      type: FLOAT
+    }
+    attribute {
+      name: "transB"
+      i: 1
+      type: INT
+    }
+  }
+  node {
+    input: "onnx::Sigmoid_166"
+    output: "167"
+    name: "Sigmoid_66"
+    op_type: "Sigmoid"
+  }
+  initializer {
+      dims: 513
+      dims: 1
+      dims: 1024
+      data_type: 1
+      name: "spectrogram_extractor.stft.conv_real.weight"
+  }
+  initializer {
+      dims: 513
+      dims: 1
+      dims: 1024
+      data_type: 1
+      name: "spectrogram_extractor.stft.conv_imag.weight"
+  }
+  initializer {
+      dims: 513
+      dims: 64
+      data_type: 1
+      name: "logmel_extractor.melW"
+  }
+  initializer {
+      dims: 64
+      data_type: 1
+      name: "bn0.weight"
+  }
+  initializer {
+      dims: 64
+      data_type: 1
+      name: "bn0.bias"
+  }
+  initializer {
+      dims: 64
+      data_type: 1
+      name: "bn0.running_mean"
+  }
+  initializer {
+      dims: 64
+      data_type: 1
+      name: "bn0.running_var"
+  }
+  initializer {
+      dims: 2048
+      dims: 2048
+      data_type: 1
+      name: "fc1.weight"
+  }
+  initializer {
+      dims: 2048
+      data_type: 1
+      name: "fc1.bias"
+  }
+  initializer {
+      dims: 527
+      dims: 2048
+      data_type: 1
+      name: "fc_audioset.weight"
+  }
+  initializer {
+      dims: 527
+      data_type: 1
+      name: "fc_audioset.bias"
+  }
+  initializer {
+      dims: 64
+      dims: 1
+      dims: 3
+      dims: 3
+      data_type: 1
+      name: "onnx::Conv_169"
+  }
+  initializer {
+      dims: 64
+      data_type: 1
+      name: "onnx::Conv_170"
+  }
+  initializer {
+      dims: 64
+      dims: 64
+      dims: 3
+      dims: 3
+      data_type: 1
+      name: "onnx::Conv_172"
+  }
+  initializer {
+      dims: 64
+      data_type: 1
+      name: "onnx::Conv_173"
+  }
+  initializer {
+      dims: 128
+      dims: 64
+      dims: 3
+      dims: 3
+      data_type: 1
+      name: "onnx::Conv_175"
+  }
+  initializer {
+      dims: 128
+      data_type: 1
+      name: "onnx::Conv_176"
+  }
+  initializer {
+      dims: 128
+      dims: 128
+      dims: 3
+      dims: 3
+      data_type: 1
+      name: "onnx::Conv_178"
+  }
+  initializer {
+      dims: 128
+      data_type: 1
+      name: "onnx::Conv_179"
+  }
+  initializer {
+      dims: 256
+      dims: 128
+      dims: 3
+      dims: 3
+      data_type: 1
+      name: "onnx::Conv_181"
+  }
+  initializer {
+      dims: 256
+      data_type: 1
+      name: "onnx::Conv_182"
+  }
+  initializer {
+      dims: 256
+      dims: 256
+      dims: 3
+      dims: 3
+      data_type: 1
+      name: "onnx::Conv_184"
+  }
+  initializer {
+      dims: 256
+      data_type: 1
+      name: "onnx::Conv_185"
+  }
+  initializer {
+      dims: 512
+      dims: 256
+      dims: 3
+      dims: 3
+      data_type: 1
+      name: "onnx::Conv_187"
+  }
+  initializer {
+      dims: 512
+      data_type: 1
+      name: "onnx::Conv_188"
+  }
+  initializer {
+      dims: 512
+      dims: 512
+      dims: 3
+      dims: 3
+      data_type: 1
+      name: "onnx::Conv_190"
+  }
+  initializer {
+      dims: 512
+      data_type: 1
+      name: "onnx::Conv_191"
+  }
+  initializer {
+      dims: 1024
+      dims: 512
+      dims: 3
+      dims: 3
+      data_type: 1
+      name: "onnx::Conv_193"
+  }
+  initializer {
+      dims: 1024
+      data_type: 1
+      name: "onnx::Conv_194"
+  }
+  initializer {
+      dims: 1024
+      dims: 1024
+      dims: 3
+      dims: 3
+      data_type: 1
+      name: "onnx::Conv_196"
+  }
+  initializer {
+      dims: 1024
+      data_type: 1
+      name: "onnx::Conv_197"
+  }
+  initializer {
+      dims: 2048
+      dims: 1024
+      dims: 3
+      dims: 3
+      data_type: 1
+      name: "onnx::Conv_199"
+  }
+  initializer {
+      dims: 2048
+      data_type: 1
+      name: "onnx::Conv_200"
+  }
+  initializer {
+      dims: 2048
+      dims: 2048
+      dims: 3
+      dims: 3
+      data_type: 1
+      name: "onnx::Conv_202"
+  }
+  initializer {
+      dims: 2048
+      data_type: 1
+      name: "onnx::Conv_203"
+  }
+  initializer {
+      data_type: 1
+      name: "onnx::Pow_204"
+  }
+  initializer {
+      data_type: 1
+      name: "onnx::Pow_205"
+  }
+  input {
+    name: "input.1"
+    type {
+      tensor_type {
+        elem_type: 1
+        shape {
+          dim {
+            dim_value: 1
+          }
+          dim {
+            dim_value: 224000
+          }
+        }
+      }
+    }
+  }
+  output {
+    name: "167"
+    type {
+      tensor_type {
+        elem_type: 1
+        shape {
+          dim {
+            dim_value: 1
+          }
+          dim {
+            dim_value: 527
+          }
+        }
+      }
+    }
+  }
+  output {
+    name: "onnx::Gemm_165"
+    type {
+      tensor_type {
+        elem_type: 1
+        shape {
+          dim {
+            dim_value: 1
+          }
+          dim {
+            dim_value: 2048
+          }
+        }
+      }
+    }
+  }
+}
+opset_import {
+  version: 9
+}

models/onnx/ailia-models/code/R9_ZSCveAHg_7s.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59429c7174a3707575581d0b4181b1e2a420bda5d1de8d5195cf0b1e07d8bdfd
+size 448078

models/onnx/ailia-models/code/README.md

@@ -0,0 +1,94 @@
+ 
+# audioset tagging cnn
+
+The Model have been used for audio tagging and sound event detection. 
+
+## audio tagging
+
+### Input
+
+Audio file
+```
+R9_ZSCveAHg_7s.wav
+https://github.com/qiuqiangkong/audioset_tagging_cnn/tree/master/resources
+```
+
+### Output
+
+```
+Speech: 0.893
+Telephone bell ringing: 0.754
+Inside, small room: 0.235
+Telephone: 0.183
+Music: 0.092
+Ringtone: 0.047
+Inside, large room or hall: 0.028
+Alarm: 0.014
+Animal: 0.009
+Vehicle: 0.008
+```
+
+## sound event detection
+
+### Input
+
+Audio file
+```
+R9_ZSCveAHg_7s.wav
+https://github.com/qiuqiangkong/audioset_tagging_cnn/tree/master/resources
+```
+
+### Output
+
+
+![Input](output.png)
+
+## Usage
+Automatically downloads the onnx and prototxt files on the first run.
+It is necessary to be connected to the Internet while downloading.
+
+You can run with other wav file by adding `--input` option.
+
+```bash
+$ python3 audioset_tagging_cnn.py --input [wav_file]
+```
+
+### audio tagging
+
+For the sample wav,
+```bash
+$ python3 audioset_tagging_cnn.py --mode audio_tagging
+```
+
+### sound event detection
+
+For the sample wav,
+```bash
+$ python3 audioset_tagging_cnn.py --mode sound_event_detection 
+
+```
+
+You can use --savepath option to change the name of the output file to save.
+```bash
+$ python audioset_tagging_cnn.py --savepath output.png
+
+```
+
+
+## Reference
+
+[audioset_tagging_cnn](https://github.com/qiuqiangkong/audioset_tagging_cnn)
+
+## Framework
+
+Pytorch
+
+## Model Format
+
+ONNX opset=9
+
+## Netron
+
+[sound_event_detection.onnx.prototxt](https://netron.app/?url=https://storage.googleapis.com/ailia-models/audio_processing/audioset_tagging_cnn/sound_event_detection.onnx.prototxt)  
+
+[audio_tagging.onnx.prototxt](https://netron.app/?url=https://storage.googleapis.com/ailia-models/audio_processing/audioset_tagging_cnn/audio_tagging.onnx.prototxt)  

models/onnx/ailia-models/code/audioset_tagging_cnn.py

@@ -0,0 +1,195 @@
+import os
+import sys
+import time
+import librosa
+import argparse
+import utilities
+import numpy as np
+import matplotlib.pyplot as plt
+import json
+
+import ailia
+
+# import original modules
+sys.path.append('../../util')
+from arg_utils import get_base_parser, update_parser  # noqa: E402
+from model_utils import check_and_download_models  # noqa: E402
+
+# logger
+from logging import getLogger  # noqa: E402
+
+logger = getLogger(__name__)
+
+# ======================
+# Parameters
+# ======================
+
+WEIGHT_TAGGING_PATH = './audio_tagging.onnx'
+MODEL_TAGGING_PATH = './audio_tagging.onnx.prototxt'
+WEIGHT_DETECTION_PATH = './sound_event_detection.onnx'
+MODEL_DETECTION_PATH = './sound_event_detection.onnx.prototxt'
+REMOTE_PATH = 'https://storage.googleapis.com/ailia-models/audioset_tagging_cnn/'
+
+WAVE_PATH = "R9_ZSCveAHg_7s.wav"
+SAVE_PATH = "output.png"
+
+
+# ======================
+# Arguemnt Parser Config
+# ======================
+
+parser = get_base_parser(
+    'audioset_tagging_cnn', WAVE_PATH, None, input_ftype='audio'
+)
+parser.add_argument('--mode', type=str, default="audio_tagging", choices=["audio_tagging", "sound_event_detection"])
+parser.add_argument('--sample_rate', type=int, default=32000)
+parser.add_argument('--window_size', type=int, default=1024)
+parser.add_argument('--hop_size', type=int, default=320)
+parser.add_argument('--mel_bins', type=int, default=64)
+parser.add_argument('--fmin', type=int, default=50)
+parser.add_argument('--fmax', type=int, default=14000) 
+parser.add_argument('-w', '--write_json', action='store_true', help='Flag to output results to json file.')
+
+args = parser.parse_args()
+
+
+def audio_tagging(args,model):
+    """Inference audio tagging result of an audio clip.
+    """
+
+    # Arugments & parameters
+    sample_rate = args.sample_rate
+    window_size = args.window_size
+    hop_size = args.hop_size
+    mel_bins = args.mel_bins
+    fmin = args.fmin
+    fmax = args.fmax
+    audio_path = args.input
+    
+    classes_num = utilities.classes_num
+    labels = utilities.labels
+
+    # Load audio
+    (waveform, _) = librosa.core.load(audio_path, sr=sample_rate, mono=True)
+
+    waveform = waveform[None, :]    # (1, audio_length)
+
+    clipwise_output = model.run(waveform)[0][0]
+
+    sorted_indexes = np.argsort(clipwise_output)[::-1]
+
+    # Print audio tagging top probabilities
+    for k in range(10):
+        print('{}: {:.3f}'.format(np.array(labels)[sorted_indexes[k]], 
+            clipwise_output[sorted_indexes[k]]))
+    if args.write_json:
+        result = []
+        for k in range(10):
+            result.append({
+                'label': np.array(labels)[sorted_indexes[k]],
+                'prob': float(clipwise_output[sorted_indexes[k]])
+            })
+        with open('output_tagging.json', 'w') as f:
+            json.dump(result, f, indent=2)
+
+    return clipwise_output, labels
+
+
+def sound_event_detection(args,model):
+    """Inference sound event detection result of an audio clip."""
+
+    # Arugments & parameters
+    sample_rate = args.sample_rate
+    window_size = args.window_size
+    hop_size = args.hop_size
+    mel_bins = args.mel_bins
+    fmin = args.fmin
+    fmax = args.fmax
+    audio_path = args.input
+
+    classes_num = utilities.classes_num
+    labels = utilities.labels
+    frames_per_second = sample_rate // hop_size
+
+    # Load audio
+    (waveform, _) = librosa.core.load(audio_path, sr=sample_rate, mono=True)
+
+    waveform = waveform[None, :]    # (1, audio_length)
+
+    framewise_output = model.run(waveform)[0][0]
+
+    print('Sound event detection result (time_steps x classes_num): {}'.format(
+        framewise_output.shape))
+
+    sorted_indexes = np.argsort(np.max(framewise_output, axis=0))[::-1]
+
+    top_k = 10  # Show top results
+    top_result_mat = framewise_output[:, sorted_indexes[0 : top_k]]    
+    """(time_steps, top_k)"""
+
+    # Plot result    
+    stft = librosa.core.stft(y=waveform[0], n_fft=window_size, 
+        hop_length=hop_size, window='hann', center=True)
+    frames_num = stft.shape[-1]
+
+    fig, axs = plt.subplots(2, 1, sharex=True, figsize=(10, 4))
+    axs[0].matshow(np.log(np.abs(stft)), origin='lower', aspect='auto', cmap='jet')
+    axs[0].set_ylabel('Frequency bins')
+    axs[0].set_title('Log spectrogram')
+    axs[1].matshow(top_result_mat.T, origin='upper', aspect='auto', cmap='jet', vmin=0, vmax=1)
+    axs[1].xaxis.set_ticks(np.arange(0, frames_num, frames_per_second))
+    axs[1].xaxis.set_ticklabels(np.arange(0, frames_num / frames_per_second))
+    axs[1].yaxis.set_ticks(np.arange(0, top_k))
+    axs[1].yaxis.set_ticklabels(np.array(labels)[sorted_indexes[0 : top_k]])
+    axs[1].yaxis.grid(color='k', linestyle='solid', linewidth=0.3, alpha=0.3)
+    axs[1].set_xlabel('Seconds')
+    axs[1].xaxis.set_ticks_position('bottom')
+
+    plt.tight_layout()
+    if args.savepath is None:
+        plt.savefig(SAVE_PATH)
+    else:
+        plt.savefig(args.savepath)
+
+    return framewise_output, labels
+
+## ======================
+## Main function
+## ======================
+
+def main(func):
+    # model files check and download
+
+    # create instance
+    if args.mode == "audio_tagging":
+        model = ailia.Net(None,WEIGHT_TAGGING_PATH)
+    elif args.mode == "sound_event_detection":
+        model = ailia.Net(None,WEIGHT_DETECTION_PATH)
+
+    logger.info('Start inference...')
+    if args.benchmark:
+        logger.info('BENCHMARK mode')
+        for c in range(5):
+            start = int(round(time.time() * 1000))
+            func(args,model)
+            end = int(round(time.time() * 1000))
+            logger.info("\tailia processing time {} ms".format(end-start))
+    else:
+        func(args,model)
+
+    logger.info('Script finished successfully.')
+
+
+
+if __name__ == '__main__':
+    check_and_download_models(WEIGHT_TAGGING_PATH, MODEL_TAGGING_PATH, REMOTE_PATH)
+    check_and_download_models(WEIGHT_DETECTION_PATH, MODEL_DETECTION_PATH, REMOTE_PATH)
+    
+    if args.mode == 'audio_tagging':
+        main(audio_tagging)
+    elif args.mode == 'sound_event_detection':
+        main(sound_event_detection)
+    else:
+        raise Exception('Error argument!')
+
+

models/onnx/ailia-models/code/class_labels_indices.csv

@@ -0,0 +1,528 @@
+index,mid,display_name
+0,/m/09x0r,"Speech"
+1,/m/05zppz,"Male speech, man speaking"
+2,/m/02zsn,"Female speech, woman speaking"
+3,/m/0ytgt,"Child speech, kid speaking"
+4,/m/01h8n0,"Conversation"
+5,/m/02qldy,"Narration, monologue"
+6,/m/0261r1,"Babbling"
+7,/m/0brhx,"Speech synthesizer"
+8,/m/07p6fty,"Shout"
+9,/m/07q4ntr,"Bellow"
+10,/m/07rwj3x,"Whoop"
+11,/m/07sr1lc,"Yell"
+12,/m/04gy_2,"Battle cry"
+13,/t/dd00135,"Children shouting"
+14,/m/03qc9zr,"Screaming"
+15,/m/02rtxlg,"Whispering"
+16,/m/01j3sz,"Laughter"
+17,/t/dd00001,"Baby laughter"
+18,/m/07r660_,"Giggle"
+19,/m/07s04w4,"Snicker"
+20,/m/07sq110,"Belly laugh"
+21,/m/07rgt08,"Chuckle, chortle"
+22,/m/0463cq4,"Crying, sobbing"
+23,/t/dd00002,"Baby cry, infant cry"
+24,/m/07qz6j3,"Whimper"
+25,/m/07qw_06,"Wail, moan"
+26,/m/07plz5l,"Sigh"
+27,/m/015lz1,"Singing"
+28,/m/0l14jd,"Choir"
+29,/m/01swy6,"Yodeling"
+30,/m/02bk07,"Chant"
+31,/m/01c194,"Mantra"
+32,/t/dd00003,"Male singing"
+33,/t/dd00004,"Female singing"
+34,/t/dd00005,"Child singing"
+35,/t/dd00006,"Synthetic singing"
+36,/m/06bxc,"Rapping"
+37,/m/02fxyj,"Humming"
+38,/m/07s2xch,"Groan"
+39,/m/07r4k75,"Grunt"
+40,/m/01w250,"Whistling"
+41,/m/0lyf6,"Breathing"
+42,/m/07mzm6,"Wheeze"
+43,/m/01d3sd,"Snoring"
+44,/m/07s0dtb,"Gasp"
+45,/m/07pyy8b,"Pant"
+46,/m/07q0yl5,"Snort"
+47,/m/01b_21,"Cough"
+48,/m/0dl9sf8,"Throat clearing"
+49,/m/01hsr_,"Sneeze"
+50,/m/07ppn3j,"Sniff"
+51,/m/06h7j,"Run"
+52,/m/07qv_x_,"Shuffle"
+53,/m/07pbtc8,"Walk, footsteps"
+54,/m/03cczk,"Chewing, mastication"
+55,/m/07pdhp0,"Biting"
+56,/m/0939n_,"Gargling"
+57,/m/01g90h,"Stomach rumble"
+58,/m/03q5_w,"Burping, eructation"
+59,/m/02p3nc,"Hiccup"
+60,/m/02_nn,"Fart"
+61,/m/0k65p,"Hands"
+62,/m/025_jnm,"Finger snapping"
+63,/m/0l15bq,"Clapping"
+64,/m/01jg02,"Heart sounds, heartbeat"
+65,/m/01jg1z,"Heart murmur"
+66,/m/053hz1,"Cheering"
+67,/m/028ght,"Applause"
+68,/m/07rkbfh,"Chatter"
+69,/m/03qtwd,"Crowd"
+70,/m/07qfr4h,"Hubbub, speech noise, speech babble"
+71,/t/dd00013,"Children playing"
+72,/m/0jbk,"Animal"
+73,/m/068hy,"Domestic animals, pets"
+74,/m/0bt9lr,"Dog"
+75,/m/05tny_,"Bark"
+76,/m/07r_k2n,"Yip"
+77,/m/07qf0zm,"Howl"
+78,/m/07rc7d9,"Bow-wow"
+79,/m/0ghcn6,"Growling"
+80,/t/dd00136,"Whimper (dog)"
+81,/m/01yrx,"Cat"
+82,/m/02yds9,"Purr"
+83,/m/07qrkrw,"Meow"
+84,/m/07rjwbb,"Hiss"
+85,/m/07r81j2,"Caterwaul"
+86,/m/0ch8v,"Livestock, farm animals, working animals"
+87,/m/03k3r,"Horse"
+88,/m/07rv9rh,"Clip-clop"
+89,/m/07q5rw0,"Neigh, whinny"
+90,/m/01xq0k1,"Cattle, bovinae"
+91,/m/07rpkh9,"Moo"
+92,/m/0239kh,"Cowbell"
+93,/m/068zj,"Pig"
+94,/t/dd00018,"Oink"
+95,/m/03fwl,"Goat"
+96,/m/07q0h5t,"Bleat"
+97,/m/07bgp,"Sheep"
+98,/m/025rv6n,"Fowl"
+99,/m/09b5t,"Chicken, rooster"
+100,/m/07st89h,"Cluck"
+101,/m/07qn5dc,"Crowing, cock-a-doodle-doo"
+102,/m/01rd7k,"Turkey"
+103,/m/07svc2k,"Gobble"
+104,/m/09ddx,"Duck"
+105,/m/07qdb04,"Quack"
+106,/m/0dbvp,"Goose"
+107,/m/07qwf61,"Honk"
+108,/m/01280g,"Wild animals"
+109,/m/0cdnk,"Roaring cats (lions, tigers)"
+110,/m/04cvmfc,"Roar"
+111,/m/015p6,"Bird"
+112,/m/020bb7,"Bird vocalization, bird call, bird song"
+113,/m/07pggtn,"Chirp, tweet"
+114,/m/07sx8x_,"Squawk"
+115,/m/0h0rv,"Pigeon, dove"
+116,/m/07r_25d,"Coo"
+117,/m/04s8yn,"Crow"
+118,/m/07r5c2p,"Caw"
+119,/m/09d5_,"Owl"
+120,/m/07r_80w,"Hoot"
+121,/m/05_wcq,"Bird flight, flapping wings"
+122,/m/01z5f,"Canidae, dogs, wolves"
+123,/m/06hps,"Rodents, rats, mice"
+124,/m/04rmv,"Mouse"
+125,/m/07r4gkf,"Patter"
+126,/m/03vt0,"Insect"
+127,/m/09xqv,"Cricket"
+128,/m/09f96,"Mosquito"
+129,/m/0h2mp,"Fly, housefly"
+130,/m/07pjwq1,"Buzz"
+131,/m/01h3n,"Bee, wasp, etc."
+132,/m/09ld4,"Frog"
+133,/m/07st88b,"Croak"
+134,/m/078jl,"Snake"
+135,/m/07qn4z3,"Rattle"
+136,/m/032n05,"Whale vocalization"
+137,/m/04rlf,"Music"
+138,/m/04szw,"Musical instrument"
+139,/m/0fx80y,"Plucked string instrument"
+140,/m/0342h,"Guitar"
+141,/m/02sgy,"Electric guitar"
+142,/m/018vs,"Bass guitar"
+143,/m/042v_gx,"Acoustic guitar"
+144,/m/06w87,"Steel guitar, slide guitar"
+145,/m/01glhc,"Tapping (guitar technique)"
+146,/m/07s0s5r,"Strum"
+147,/m/018j2,"Banjo"
+148,/m/0jtg0,"Sitar"
+149,/m/04rzd,"Mandolin"
+150,/m/01bns_,"Zither"
+151,/m/07xzm,"Ukulele"
+152,/m/05148p4,"Keyboard (musical)"
+153,/m/05r5c,"Piano"
+154,/m/01s0ps,"Electric piano"
+155,/m/013y1f,"Organ"
+156,/m/03xq_f,"Electronic organ"
+157,/m/03gvt,"Hammond organ"
+158,/m/0l14qv,"Synthesizer"
+159,/m/01v1d8,"Sampler"
+160,/m/03q5t,"Harpsichord"
+161,/m/0l14md,"Percussion"
+162,/m/02hnl,"Drum kit"
+163,/m/0cfdd,"Drum machine"
+164,/m/026t6,"Drum"
+165,/m/06rvn,"Snare drum"
+166,/m/03t3fj,"Rimshot"
+167,/m/02k_mr,"Drum roll"
+168,/m/0bm02,"Bass drum"
+169,/m/011k_j,"Timpani"
+170,/m/01p970,"Tabla"
+171,/m/01qbl,"Cymbal"
+172,/m/03qtq,"Hi-hat"
+173,/m/01sm1g,"Wood block"
+174,/m/07brj,"Tambourine"
+175,/m/05r5wn,"Rattle (instrument)"
+176,/m/0xzly,"Maraca"
+177,/m/0mbct,"Gong"
+178,/m/016622,"Tubular bells"
+179,/m/0j45pbj,"Mallet percussion"
+180,/m/0dwsp,"Marimba, xylophone"
+181,/m/0dwtp,"Glockenspiel"
+182,/m/0dwt5,"Vibraphone"
+183,/m/0l156b,"Steelpan"
+184,/m/05pd6,"Orchestra"
+185,/m/01kcd,"Brass instrument"
+186,/m/0319l,"French horn"
+187,/m/07gql,"Trumpet"
+188,/m/07c6l,"Trombone"
+189,/m/0l14_3,"Bowed string instrument"
+190,/m/02qmj0d,"String section"
+191,/m/07y_7,"Violin, fiddle"
+192,/m/0d8_n,"Pizzicato"
+193,/m/01xqw,"Cello"
+194,/m/02fsn,"Double bass"
+195,/m/085jw,"Wind instrument, woodwind instrument"
+196,/m/0l14j_,"Flute"
+197,/m/06ncr,"Saxophone"
+198,/m/01wy6,"Clarinet"
+199,/m/03m5k,"Harp"
+200,/m/0395lw,"Bell"
+201,/m/03w41f,"Church bell"
+202,/m/027m70_,"Jingle bell"
+203,/m/0gy1t2s,"Bicycle bell"
+204,/m/07n_g,"Tuning fork"
+205,/m/0f8s22,"Chime"
+206,/m/026fgl,"Wind chime"
+207,/m/0150b9,"Change ringing (campanology)"
+208,/m/03qjg,"Harmonica"
+209,/m/0mkg,"Accordion"
+210,/m/0192l,"Bagpipes"
+211,/m/02bxd,"Didgeridoo"
+212,/m/0l14l2,"Shofar"
+213,/m/07kc_,"Theremin"
+214,/m/0l14t7,"Singing bowl"
+215,/m/01hgjl,"Scratching (performance technique)"
+216,/m/064t9,"Pop music"
+217,/m/0glt670,"Hip hop music"
+218,/m/02cz_7,"Beatboxing"
+219,/m/06by7,"Rock music"
+220,/m/03lty,"Heavy metal"
+221,/m/05r6t,"Punk rock"
+222,/m/0dls3,"Grunge"
+223,/m/0dl5d,"Progressive rock"
+224,/m/07sbbz2,"Rock and roll"
+225,/m/05w3f,"Psychedelic rock"
+226,/m/06j6l,"Rhythm and blues"
+227,/m/0gywn,"Soul music"
+228,/m/06cqb,"Reggae"
+229,/m/01lyv,"Country"
+230,/m/015y_n,"Swing music"
+231,/m/0gg8l,"Bluegrass"
+232,/m/02x8m,"Funk"
+233,/m/02w4v,"Folk music"
+234,/m/06j64v,"Middle Eastern music"
+235,/m/03_d0,"Jazz"
+236,/m/026z9,"Disco"
+237,/m/0ggq0m,"Classical music"
+238,/m/05lls,"Opera"
+239,/m/02lkt,"Electronic music"
+240,/m/03mb9,"House music"
+241,/m/07gxw,"Techno"
+242,/m/07s72n,"Dubstep"
+243,/m/0283d,"Drum and bass"
+244,/m/0m0jc,"Electronica"
+245,/m/08cyft,"Electronic dance music"
+246,/m/0fd3y,"Ambient music"
+247,/m/07lnk,"Trance music"
+248,/m/0g293,"Music of Latin America"
+249,/m/0ln16,"Salsa music"
+250,/m/0326g,"Flamenco"
+251,/m/0155w,"Blues"
+252,/m/05fw6t,"Music for children"
+253,/m/02v2lh,"New-age music"
+254,/m/0y4f8,"Vocal music"
+255,/m/0z9c,"A capella"
+256,/m/0164x2,"Music of Africa"
+257,/m/0145m,"Afrobeat"
+258,/m/02mscn,"Christian music"
+259,/m/016cjb,"Gospel music"
+260,/m/028sqc,"Music of Asia"
+261,/m/015vgc,"Carnatic music"
+262,/m/0dq0md,"Music of Bollywood"
+263,/m/06rqw,"Ska"
+264,/m/02p0sh1,"Traditional music"
+265,/m/05rwpb,"Independent music"
+266,/m/074ft,"Song"
+267,/m/025td0t,"Background music"
+268,/m/02cjck,"Theme music"
+269,/m/03r5q_,"Jingle (music)"
+270,/m/0l14gg,"Soundtrack music"
+271,/m/07pkxdp,"Lullaby"
+272,/m/01z7dr,"Video game music"
+273,/m/0140xf,"Christmas music"
+274,/m/0ggx5q,"Dance music"
+275,/m/04wptg,"Wedding music"
+276,/t/dd00031,"Happy music"
+277,/t/dd00032,"Funny music"
+278,/t/dd00033,"Sad music"
+279,/t/dd00034,"Tender music"
+280,/t/dd00035,"Exciting music"
+281,/t/dd00036,"Angry music"
+282,/t/dd00037,"Scary music"
+283,/m/03m9d0z,"Wind"
+284,/m/09t49,"Rustling leaves"
+285,/t/dd00092,"Wind noise (microphone)"
+286,/m/0jb2l,"Thunderstorm"
+287,/m/0ngt1,"Thunder"
+288,/m/0838f,"Water"
+289,/m/06mb1,"Rain"
+290,/m/07r10fb,"Raindrop"
+291,/t/dd00038,"Rain on surface"
+292,/m/0j6m2,"Stream"
+293,/m/0j2kx,"Waterfall"
+294,/m/05kq4,"Ocean"
+295,/m/034srq,"Waves, surf"
+296,/m/06wzb,"Steam"
+297,/m/07swgks,"Gurgling"
+298,/m/02_41,"Fire"
+299,/m/07pzfmf,"Crackle"
+300,/m/07yv9,"Vehicle"
+301,/m/019jd,"Boat, Water vehicle"
+302,/m/0hsrw,"Sailboat, sailing ship"
+303,/m/056ks2,"Rowboat, canoe, kayak"
+304,/m/02rlv9,"Motorboat, speedboat"
+305,/m/06q74,"Ship"
+306,/m/012f08,"Motor vehicle (road)"
+307,/m/0k4j,"Car"
+308,/m/0912c9,"Vehicle horn, car horn, honking"
+309,/m/07qv_d5,"Toot"
+310,/m/02mfyn,"Car alarm"
+311,/m/04gxbd,"Power windows, electric windows"
+312,/m/07rknqz,"Skidding"
+313,/m/0h9mv,"Tire squeal"
+314,/t/dd00134,"Car passing by"
+315,/m/0ltv,"Race car, auto racing"
+316,/m/07r04,"Truck"
+317,/m/0gvgw0,"Air brake"
+318,/m/05x_td,"Air horn, truck horn"
+319,/m/02rhddq,"Reversing beeps"
+320,/m/03cl9h,"Ice cream truck, ice cream van"
+321,/m/01bjv,"Bus"
+322,/m/03j1ly,"Emergency vehicle"
+323,/m/04qvtq,"Police car (siren)"
+324,/m/012n7d,"Ambulance (siren)"
+325,/m/012ndj,"Fire engine, fire truck (siren)"
+326,/m/04_sv,"Motorcycle"
+327,/m/0btp2,"Traffic noise, roadway noise"
+328,/m/06d_3,"Rail transport"
+329,/m/07jdr,"Train"
+330,/m/04zmvq,"Train whistle"
+331,/m/0284vy3,"Train horn"
+332,/m/01g50p,"Railroad car, train wagon"
+333,/t/dd00048,"Train wheels squealing"
+334,/m/0195fx,"Subway, metro, underground"
+335,/m/0k5j,"Aircraft"
+336,/m/014yck,"Aircraft engine"
+337,/m/04229,"Jet engine"
+338,/m/02l6bg,"Propeller, airscrew"
+339,/m/09ct_,"Helicopter"
+340,/m/0cmf2,"Fixed-wing aircraft, airplane"
+341,/m/0199g,"Bicycle"
+342,/m/06_fw,"Skateboard"
+343,/m/02mk9,"Engine"
+344,/t/dd00065,"Light engine (high frequency)"
+345,/m/08j51y,"Dental drill, dentist's drill"
+346,/m/01yg9g,"Lawn mower"
+347,/m/01j4z9,"Chainsaw"
+348,/t/dd00066,"Medium engine (mid frequency)"
+349,/t/dd00067,"Heavy engine (low frequency)"
+350,/m/01h82_,"Engine knocking"
+351,/t/dd00130,"Engine starting"
+352,/m/07pb8fc,"Idling"
+353,/m/07q2z82,"Accelerating, revving, vroom"
+354,/m/02dgv,"Door"
+355,/m/03wwcy,"Doorbell"
+356,/m/07r67yg,"Ding-dong"
+357,/m/02y_763,"Sliding door"
+358,/m/07rjzl8,"Slam"
+359,/m/07r4wb8,"Knock"
+360,/m/07qcpgn,"Tap"
+361,/m/07q6cd_,"Squeak"
+362,/m/0642b4,"Cupboard open or close"
+363,/m/0fqfqc,"Drawer open or close"
+364,/m/04brg2,"Dishes, pots, and pans"
+365,/m/023pjk,"Cutlery, silverware"
+366,/m/07pn_8q,"Chopping (food)"
+367,/m/0dxrf,"Frying (food)"
+368,/m/0fx9l,"Microwave oven"
+369,/m/02pjr4,"Blender"
+370,/m/02jz0l,"Water tap, faucet"
+371,/m/0130jx,"Sink (filling or washing)"
+372,/m/03dnzn,"Bathtub (filling or washing)"
+373,/m/03wvsk,"Hair dryer"
+374,/m/01jt3m,"Toilet flush"
+375,/m/012xff,"Toothbrush"
+376,/m/04fgwm,"Electric toothbrush"
+377,/m/0d31p,"Vacuum cleaner"
+378,/m/01s0vc,"Zipper (clothing)"
+379,/m/03v3yw,"Keys jangling"
+380,/m/0242l,"Coin (dropping)"
+381,/m/01lsmm,"Scissors"
+382,/m/02g901,"Electric shaver, electric razor"
+383,/m/05rj2,"Shuffling cards"
+384,/m/0316dw,"Typing"
+385,/m/0c2wf,"Typewriter"
+386,/m/01m2v,"Computer keyboard"
+387,/m/081rb,"Writing"
+388,/m/07pp_mv,"Alarm"
+389,/m/07cx4,"Telephone"
+390,/m/07pp8cl,"Telephone bell ringing"
+391,/m/01hnzm,"Ringtone"
+392,/m/02c8p,"Telephone dialing, DTMF"
+393,/m/015jpf,"Dial tone"
+394,/m/01z47d,"Busy signal"
+395,/m/046dlr,"Alarm clock"
+396,/m/03kmc9,"Siren"
+397,/m/0dgbq,"Civil defense siren"
+398,/m/030rvx,"Buzzer"
+399,/m/01y3hg,"Smoke detector, smoke alarm"
+400,/m/0c3f7m,"Fire alarm"
+401,/m/04fq5q,"Foghorn"
+402,/m/0l156k,"Whistle"
+403,/m/06hck5,"Steam whistle"
+404,/t/dd00077,"Mechanisms"
+405,/m/02bm9n,"Ratchet, pawl"
+406,/m/01x3z,"Clock"
+407,/m/07qjznt,"Tick"
+408,/m/07qjznl,"Tick-tock"
+409,/m/0l7xg,"Gears"
+410,/m/05zc1,"Pulleys"
+411,/m/0llzx,"Sewing machine"
+412,/m/02x984l,"Mechanical fan"
+413,/m/025wky1,"Air conditioning"
+414,/m/024dl,"Cash register"
+415,/m/01m4t,"Printer"
+416,/m/0dv5r,"Camera"
+417,/m/07bjf,"Single-lens reflex camera"
+418,/m/07k1x,"Tools"
+419,/m/03l9g,"Hammer"
+420,/m/03p19w,"Jackhammer"
+421,/m/01b82r,"Sawing"
+422,/m/02p01q,"Filing (rasp)"
+423,/m/023vsd,"Sanding"
+424,/m/0_ksk,"Power tool"
+425,/m/01d380,"Drill"
+426,/m/014zdl,"Explosion"
+427,/m/032s66,"Gunshot, gunfire"
+428,/m/04zjc,"Machine gun"
+429,/m/02z32qm,"Fusillade"
+430,/m/0_1c,"Artillery fire"
+431,/m/073cg4,"Cap gun"
+432,/m/0g6b5,"Fireworks"
+433,/g/122z_qxw,"Firecracker"
+434,/m/07qsvvw,"Burst, pop"
+435,/m/07pxg6y,"Eruption"
+436,/m/07qqyl4,"Boom"
+437,/m/083vt,"Wood"
+438,/m/07pczhz,"Chop"
+439,/m/07pl1bw,"Splinter"
+440,/m/07qs1cx,"Crack"
+441,/m/039jq,"Glass"
+442,/m/07q7njn,"Chink, clink"
+443,/m/07rn7sz,"Shatter"
+444,/m/04k94,"Liquid"
+445,/m/07rrlb6,"Splash, splatter"
+446,/m/07p6mqd,"Slosh"
+447,/m/07qlwh6,"Squish"
+448,/m/07r5v4s,"Drip"
+449,/m/07prgkl,"Pour"
+450,/m/07pqc89,"Trickle, dribble"
+451,/t/dd00088,"Gush"
+452,/m/07p7b8y,"Fill (with liquid)"
+453,/m/07qlf79,"Spray"
+454,/m/07ptzwd,"Pump (liquid)"
+455,/m/07ptfmf,"Stir"
+456,/m/0dv3j,"Boiling"
+457,/m/0790c,"Sonar"
+458,/m/0dl83,"Arrow"
+459,/m/07rqsjt,"Whoosh, swoosh, swish"
+460,/m/07qnq_y,"Thump, thud"
+461,/m/07rrh0c,"Thunk"
+462,/m/0b_fwt,"Electronic tuner"
+463,/m/02rr_,"Effects unit"
+464,/m/07m2kt,"Chorus effect"
+465,/m/018w8,"Basketball bounce"
+466,/m/07pws3f,"Bang"
+467,/m/07ryjzk,"Slap, smack"
+468,/m/07rdhzs,"Whack, thwack"
+469,/m/07pjjrj,"Smash, crash"
+470,/m/07pc8lb,"Breaking"
+471,/m/07pqn27,"Bouncing"
+472,/m/07rbp7_,"Whip"
+473,/m/07pyf11,"Flap"
+474,/m/07qb_dv,"Scratch"
+475,/m/07qv4k0,"Scrape"
+476,/m/07pdjhy,"Rub"
+477,/m/07s8j8t,"Roll"
+478,/m/07plct2,"Crushing"
+479,/t/dd00112,"Crumpling, crinkling"
+480,/m/07qcx4z,"Tearing"
+481,/m/02fs_r,"Beep, bleep"
+482,/m/07qwdck,"Ping"
+483,/m/07phxs1,"Ding"
+484,/m/07rv4dm,"Clang"
+485,/m/07s02z0,"Squeal"
+486,/m/07qh7jl,"Creak"
+487,/m/07qwyj0,"Rustle"
+488,/m/07s34ls,"Whir"
+489,/m/07qmpdm,"Clatter"
+490,/m/07p9k1k,"Sizzle"
+491,/m/07qc9xj,"Clicking"
+492,/m/07rwm0c,"Clickety-clack"
+493,/m/07phhsh,"Rumble"
+494,/m/07qyrcz,"Plop"
+495,/m/07qfgpx,"Jingle, tinkle"
+496,/m/07rcgpl,"Hum"
+497,/m/07p78v5,"Zing"
+498,/t/dd00121,"Boing"
+499,/m/07s12q4,"Crunch"
+500,/m/028v0c,"Silence"
+501,/m/01v_m0,"Sine wave"
+502,/m/0b9m1,"Harmonic"
+503,/m/0hdsk,"Chirp tone"
+504,/m/0c1dj,"Sound effect"
+505,/m/07pt_g0,"Pulse"
+506,/t/dd00125,"Inside, small room"
+507,/t/dd00126,"Inside, large room or hall"
+508,/t/dd00127,"Inside, public space"
+509,/t/dd00128,"Outside, urban or manmade"
+510,/t/dd00129,"Outside, rural or natural"
+511,/m/01b9nn,"Reverberation"
+512,/m/01jnbd,"Echo"
+513,/m/096m7z,"Noise"
+514,/m/06_y0by,"Environmental noise"
+515,/m/07rgkc5,"Static"
+516,/m/06xkwv,"Mains hum"
+517,/m/0g12c5,"Distortion"
+518,/m/08p9q4,"Sidetone"
+519,/m/07szfh9,"Cacophony"
+520,/m/0chx_,"White noise"
+521,/m/0cj0r,"Pink noise"
+522,/m/07p_0gm,"Throbbing"
+523,/m/01jwx6,"Vibration"
+524,/m/07c52,"Television"
+525,/m/06bz3,"Radio"
+526,/m/07hvw1,"Field recording"

models/onnx/ailia-models/code/utilities.py

@@ -0,0 +1,29 @@
+import os
+import csv
+
+def create_folder(fd):
+    if not os.path.exists(fd):
+        os.makedirs(fd)
+        
+def get_filename(path):
+    path = os.path.realpath(path)
+    na_ext = path.split('/')[-1]
+    na = os.path.splitext(na_ext)[0]
+    return na
+
+
+
+# Load label
+with open('class_labels_indices.csv', 'r') as f:
+    reader = csv.reader(f, delimiter=',')
+    lines = list(reader)
+
+labels = []
+ids = []    # Each label has a unique id such as "/m/068hy"
+for i1 in range(1, len(lines)):
+    id = lines[i1][1]
+    label = lines[i1][2]
+    ids.append(id)
+    labels.append(label)
+
+classes_num = len(labels)

models/onnx/ailia-models/sound_event_detection.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01d426f5ca083ca9934d0d39fe38de31a91b7e3ed7d0a797d4c67e743f1555dc
+size 327325913

models/onnx/ailia-models/sound_event_detection.onnx.prototxt

@@ -0,0 +1,1759 @@
+ir_version: 4
+producer_name: "pytorch"
+producer_version: "1.11.0"
+model_version: 0
+graph {
+  name: "torch-jit-export"
+  node {
+    input: "input.1"
+    output: "onnx::Pad_85"
+    name: "Unsqueeze_0"
+    op_type: "Unsqueeze"
+    attribute {
+      name: "axes"
+      ints: 1
+      type: INTS
+    }
+  }
+  node {
+    input: "onnx::Pad_85"
+    output: "input"
+    name: "Pad_1"
+    op_type: "Pad"
+    attribute {
+      name: "mode"
+      s: "reflect"
+      type: STRING
+    }
+    attribute {
+      name: "pads"
+      ints: 0
+      ints: 0
+      ints: 512
+      ints: 0
+      ints: 0
+      ints: 512
+      type: INTS
+    }
+  }
+  node {
+    input: "input"
+    input: "spectrogram_extractor.stft.conv_real.weight"
+    output: "onnx::Unsqueeze_87"
+    name: "Conv_2"
+    op_type: "Conv"
+    attribute {
+      name: "dilations"
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "group"
+      i: 1
+      type: INT
+    }
+    attribute {
+      name: "kernel_shape"
+      ints: 1024
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 0
+      ints: 0
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 320
+      type: INTS
+    }
+  }
+  node {
+    input: "input"
+    input: "spectrogram_extractor.stft.conv_imag.weight"
+    output: "onnx::Unsqueeze_88"
+    name: "Conv_3"
+    op_type: "Conv"
+    attribute {
+      name: "dilations"
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "group"
+      i: 1
+      type: INT
+    }
+    attribute {
+      name: "kernel_shape"
+      ints: 1024
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 0
+      ints: 0
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 320
+      type: INTS
+    }
+  }
+  node {
+    input: "onnx::Unsqueeze_87"
+    output: "onnx::Transpose_89"
+    name: "Unsqueeze_4"
+    op_type: "Unsqueeze"
+    attribute {
+      name: "axes"
+      ints: 1
+      type: INTS
+    }
+  }
+  node {
+    input: "onnx::Transpose_89"
+    output: "real"
+    name: "Transpose_5"
+    op_type: "Transpose"
+    attribute {
+      name: "perm"
+      ints: 0
+      ints: 1
+      ints: 3
+      ints: 2
+      type: INTS
+    }
+  }
+  node {
+    input: "onnx::Unsqueeze_88"
+    output: "onnx::Transpose_91"
+    name: "Unsqueeze_6"
+    op_type: "Unsqueeze"
+    attribute {
+      name: "axes"
+      ints: 1
+      type: INTS
+    }
+  }
+  node {
+    input: "onnx::Transpose_91"
+    output: "imag"
+    name: "Transpose_7"
+    op_type: "Transpose"
+    attribute {
+      name: "perm"
+      ints: 0
+      ints: 1
+      ints: 3
+      ints: 2
+      type: INTS
+    }
+  }
+  node {
+    input: "real"
+    input: "onnx::Pow_242"
+    output: "onnx::Add_95"
+    name: "Pow_8"
+    op_type: "Pow"
+  }
+  node {
+    input: "imag"
+    input: "onnx::Pow_243"
+    output: "onnx::Add_98"
+    name: "Pow_9"
+    op_type: "Pow"
+  }
+  node {
+    input: "onnx::Add_95"
+    input: "onnx::Add_98"
+    output: "onnx::MatMul_99"
+    name: "Add_10"
+    op_type: "Add"
+  }
+  node {
+    input: "onnx::MatMul_99"
+    input: "logmel_extractor.melW"
+    output: "mel_spectrogram"
+    name: "MatMul_11"
+    op_type: "MatMul"
+  }
+  node {
+    input: "mel_spectrogram"
+    output: "onnx::Log_101"
+    name: "Clip_12"
+    op_type: "Clip"
+    attribute {
+      name: "max"
+      f: inf
+      type: FLOAT
+    }
+    attribute {
+      name: "min"
+      f: 1.000000013351432e-10
+      type: FLOAT
+    }
+  }
+  node {
+    input: "onnx::Log_101"
+    output: "onnx::Div_102"
+    name: "Log_13"
+    op_type: "Log"
+  }
+  node {
+    output: "onnx::Div_103"
+    name: "Constant_14"
+    op_type: "Constant"
+    attribute {
+      name: "value"
+      t {
+        dims: 1
+        data_type: 1
+      }
+      type: TENSOR
+    }
+  }
+  node {
+    input: "onnx::Div_102"
+    input: "onnx::Div_103"
+    output: "onnx::Mul_104"
+    name: "Div_15"
+    op_type: "Div"
+  }
+  node {
+    output: "onnx::Mul_105"
+    name: "Constant_16"
+    op_type: "Constant"
+    attribute {
+      name: "value"
+      t {
+        data_type: 1
+      }
+      type: TENSOR
+    }
+  }
+  node {
+    input: "onnx::Mul_104"
+    input: "onnx::Mul_105"
+    output: "onnx::Sub_106"
+    name: "Mul_17"
+    op_type: "Mul"
+  }
+  node {
+    output: "onnx::Sub_107"
+    name: "Constant_18"
+    op_type: "Constant"
+    attribute {
+      name: "value"
+      t {
+        data_type: 1
+      }
+      type: TENSOR
+    }
+  }
+  node {
+    input: "onnx::Sub_106"
+    input: "onnx::Sub_107"
+    output: "onnx::Transpose_108"
+    name: "Sub_19"
+    op_type: "Sub"
+  }
+  node {
+    input: "onnx::Transpose_108"
+    output: "input.4"
+    name: "Transpose_20"
+    op_type: "Transpose"
+    attribute {
+      name: "perm"
+      ints: 0
+      ints: 3
+      ints: 2
+      ints: 1
+      type: INTS
+    }
+  }
+  node {
+    input: "input.4"
+    input: "bn0.weight"
+    input: "bn0.bias"
+    input: "bn0.running_mean"
+    input: "bn0.running_var"
+    output: "onnx::Transpose_110"
+    name: "BatchNormalization_21"
+    op_type: "BatchNormalization"
+    attribute {
+      name: "epsilon"
+      f: 9.999999747378752e-06
+      type: FLOAT
+    }
+    attribute {
+      name: "momentum"
+      f: 0.8999999761581421
+      type: FLOAT
+    }
+  }
+  node {
+    input: "onnx::Transpose_110"
+    output: "input.8"
+    name: "Transpose_22"
+    op_type: "Transpose"
+    attribute {
+      name: "perm"
+      ints: 0
+      ints: 3
+      ints: 2
+      ints: 1
+      type: INTS
+    }
+  }
+  node {
+    input: "input.8"
+    input: "onnx::Conv_207"
+    input: "onnx::Conv_208"
+    output: "onnx::Relu_206"
+    name: "Conv_23"
+    op_type: "Conv"
+    attribute {
+      name: "dilations"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "group"
+      i: 1
+      type: INT
+    }
+    attribute {
+      name: "kernel_shape"
+      ints: 3
+      ints: 3
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 1
+      ints: 1
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+  }
+  node {
+    input: "onnx::Relu_206"
+    output: "onnx::Conv_114"
+    name: "Relu_24"
+    op_type: "Relu"
+  }
+  node {
+    input: "onnx::Conv_114"
+    input: "onnx::Conv_210"
+    input: "onnx::Conv_211"
+    output: "onnx::Relu_209"
+    name: "Conv_25"
+    op_type: "Conv"
+    attribute {
+      name: "dilations"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "group"
+      i: 1
+      type: INT
+    }
+    attribute {
+      name: "kernel_shape"
+      ints: 3
+      ints: 3
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 1
+      ints: 1
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+  }
+  node {
+    input: "onnx::Relu_209"
+    output: "onnx::Pad_117"
+    name: "Relu_26"
+    op_type: "Relu"
+  }
+  node {
+    input: "onnx::Pad_117"
+    output: "onnx::AveragePool_118"
+    name: "Pad_27"
+    op_type: "Pad"
+    attribute {
+      name: "mode"
+      s: "constant"
+      type: STRING
+    }
+    attribute {
+      name: "pads"
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      type: INTS
+    }
+    attribute {
+      name: "value"
+      f: 0.0
+      type: FLOAT
+    }
+  }
+  node {
+    input: "onnx::AveragePool_118"
+    output: "x"
+    name: "AveragePool_28"
+    op_type: "AveragePool"
+    attribute {
+      name: "kernel_shape"
+      ints: 2
+      ints: 2
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 2
+      ints: 2
+      type: INTS
+    }
+  }
+  node {
+    input: "x"
+    input: "onnx::Conv_213"
+    input: "onnx::Conv_214"
+    output: "onnx::Relu_212"
+    name: "Conv_29"
+    op_type: "Conv"
+    attribute {
+      name: "dilations"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "group"
+      i: 1
+      type: INT
+    }
+    attribute {
+      name: "kernel_shape"
+      ints: 3
+      ints: 3
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 1
+      ints: 1
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+  }
+  node {
+    input: "onnx::Relu_212"
+    output: "onnx::Conv_122"
+    name: "Relu_30"
+    op_type: "Relu"
+  }
+  node {
+    input: "onnx::Conv_122"
+    input: "onnx::Conv_216"
+    input: "onnx::Conv_217"
+    output: "onnx::Relu_215"
+    name: "Conv_31"
+    op_type: "Conv"
+    attribute {
+      name: "dilations"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "group"
+      i: 1
+      type: INT
+    }
+    attribute {
+      name: "kernel_shape"
+      ints: 3
+      ints: 3
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 1
+      ints: 1
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+  }
+  node {
+    input: "onnx::Relu_215"
+    output: "onnx::Pad_125"
+    name: "Relu_32"
+    op_type: "Relu"
+  }
+  node {
+    input: "onnx::Pad_125"
+    output: "onnx::AveragePool_126"
+    name: "Pad_33"
+    op_type: "Pad"
+    attribute {
+      name: "mode"
+      s: "constant"
+      type: STRING
+    }
+    attribute {
+      name: "pads"
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      type: INTS
+    }
+    attribute {
+      name: "value"
+      f: 0.0
+      type: FLOAT
+    }
+  }
+  node {
+    input: "onnx::AveragePool_126"
+    output: "x.3"
+    name: "AveragePool_34"
+    op_type: "AveragePool"
+    attribute {
+      name: "kernel_shape"
+      ints: 2
+      ints: 2
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 2
+      ints: 2
+      type: INTS
+    }
+  }
+  node {
+    input: "x.3"
+    input: "onnx::Conv_219"
+    input: "onnx::Conv_220"
+    output: "onnx::Relu_218"
+    name: "Conv_35"
+    op_type: "Conv"
+    attribute {
+      name: "dilations"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "group"
+      i: 1
+      type: INT
+    }
+    attribute {
+      name: "kernel_shape"
+      ints: 3
+      ints: 3
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 1
+      ints: 1
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+  }
+  node {
+    input: "onnx::Relu_218"
+    output: "onnx::Conv_130"
+    name: "Relu_36"
+    op_type: "Relu"
+  }
+  node {
+    input: "onnx::Conv_130"
+    input: "onnx::Conv_222"
+    input: "onnx::Conv_223"
+    output: "onnx::Relu_221"
+    name: "Conv_37"
+    op_type: "Conv"
+    attribute {
+      name: "dilations"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "group"
+      i: 1
+      type: INT
+    }
+    attribute {
+      name: "kernel_shape"
+      ints: 3
+      ints: 3
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 1
+      ints: 1
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+  }
+  node {
+    input: "onnx::Relu_221"
+    output: "onnx::Pad_133"
+    name: "Relu_38"
+    op_type: "Relu"
+  }
+  node {
+    input: "onnx::Pad_133"
+    output: "onnx::AveragePool_134"
+    name: "Pad_39"
+    op_type: "Pad"
+    attribute {
+      name: "mode"
+      s: "constant"
+      type: STRING
+    }
+    attribute {
+      name: "pads"
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      type: INTS
+    }
+    attribute {
+      name: "value"
+      f: 0.0
+      type: FLOAT
+    }
+  }
+  node {
+    input: "onnx::AveragePool_134"
+    output: "x.7"
+    name: "AveragePool_40"
+    op_type: "AveragePool"
+    attribute {
+      name: "kernel_shape"
+      ints: 2
+      ints: 2
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 2
+      ints: 2
+      type: INTS
+    }
+  }
+  node {
+    input: "x.7"
+    input: "onnx::Conv_225"
+    input: "onnx::Conv_226"
+    output: "onnx::Relu_224"
+    name: "Conv_41"
+    op_type: "Conv"
+    attribute {
+      name: "dilations"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "group"
+      i: 1
+      type: INT
+    }
+    attribute {
+      name: "kernel_shape"
+      ints: 3
+      ints: 3
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 1
+      ints: 1
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+  }
+  node {
+    input: "onnx::Relu_224"
+    output: "onnx::Conv_138"
+    name: "Relu_42"
+    op_type: "Relu"
+  }
+  node {
+    input: "onnx::Conv_138"
+    input: "onnx::Conv_228"
+    input: "onnx::Conv_229"
+    output: "onnx::Relu_227"
+    name: "Conv_43"
+    op_type: "Conv"
+    attribute {
+      name: "dilations"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "group"
+      i: 1
+      type: INT
+    }
+    attribute {
+      name: "kernel_shape"
+      ints: 3
+      ints: 3
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 1
+      ints: 1
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+  }
+  node {
+    input: "onnx::Relu_227"
+    output: "onnx::Pad_141"
+    name: "Relu_44"
+    op_type: "Relu"
+  }
+  node {
+    input: "onnx::Pad_141"
+    output: "onnx::AveragePool_142"
+    name: "Pad_45"
+    op_type: "Pad"
+    attribute {
+      name: "mode"
+      s: "constant"
+      type: STRING
+    }
+    attribute {
+      name: "pads"
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      type: INTS
+    }
+    attribute {
+      name: "value"
+      f: 0.0
+      type: FLOAT
+    }
+  }
+  node {
+    input: "onnx::AveragePool_142"
+    output: "x.11"
+    name: "AveragePool_46"
+    op_type: "AveragePool"
+    attribute {
+      name: "kernel_shape"
+      ints: 2
+      ints: 2
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 2
+      ints: 2
+      type: INTS
+    }
+  }
+  node {
+    input: "x.11"
+    input: "onnx::Conv_231"
+    input: "onnx::Conv_232"
+    output: "onnx::Relu_230"
+    name: "Conv_47"
+    op_type: "Conv"
+    attribute {
+      name: "dilations"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "group"
+      i: 1
+      type: INT
+    }
+    attribute {
+      name: "kernel_shape"
+      ints: 3
+      ints: 3
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 1
+      ints: 1
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+  }
+  node {
+    input: "onnx::Relu_230"
+    output: "onnx::Conv_146"
+    name: "Relu_48"
+    op_type: "Relu"
+  }
+  node {
+    input: "onnx::Conv_146"
+    input: "onnx::Conv_234"
+    input: "onnx::Conv_235"
+    output: "onnx::Relu_233"
+    name: "Conv_49"
+    op_type: "Conv"
+    attribute {
+      name: "dilations"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "group"
+      i: 1
+      type: INT
+    }
+    attribute {
+      name: "kernel_shape"
+      ints: 3
+      ints: 3
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 1
+      ints: 1
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+  }
+  node {
+    input: "onnx::Relu_233"
+    output: "onnx::Pad_149"
+    name: "Relu_50"
+    op_type: "Relu"
+  }
+  node {
+    input: "onnx::Pad_149"
+    output: "onnx::AveragePool_150"
+    name: "Pad_51"
+    op_type: "Pad"
+    attribute {
+      name: "mode"
+      s: "constant"
+      type: STRING
+    }
+    attribute {
+      name: "pads"
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      type: INTS
+    }
+    attribute {
+      name: "value"
+      f: 0.0
+      type: FLOAT
+    }
+  }
+  node {
+    input: "onnx::AveragePool_150"
+    output: "x.15"
+    name: "AveragePool_52"
+    op_type: "AveragePool"
+    attribute {
+      name: "kernel_shape"
+      ints: 2
+      ints: 2
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 2
+      ints: 2
+      type: INTS
+    }
+  }
+  node {
+    input: "x.15"
+    input: "onnx::Conv_237"
+    input: "onnx::Conv_238"
+    output: "onnx::Relu_236"
+    name: "Conv_53"
+    op_type: "Conv"
+    attribute {
+      name: "dilations"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "group"
+      i: 1
+      type: INT
+    }
+    attribute {
+      name: "kernel_shape"
+      ints: 3
+      ints: 3
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 1
+      ints: 1
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+  }
+  node {
+    input: "onnx::Relu_236"
+    output: "onnx::Conv_154"
+    name: "Relu_54"
+    op_type: "Relu"
+  }
+  node {
+    input: "onnx::Conv_154"
+    input: "onnx::Conv_240"
+    input: "onnx::Conv_241"
+    output: "onnx::Relu_239"
+    name: "Conv_55"
+    op_type: "Conv"
+    attribute {
+      name: "dilations"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "group"
+      i: 1
+      type: INT
+    }
+    attribute {
+      name: "kernel_shape"
+      ints: 3
+      ints: 3
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 1
+      ints: 1
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+  }
+  node {
+    input: "onnx::Relu_239"
+    output: "onnx::Pad_157"
+    name: "Relu_56"
+    op_type: "Relu"
+  }
+  node {
+    input: "onnx::Pad_157"
+    output: "onnx::AveragePool_158"
+    name: "Pad_57"
+    op_type: "Pad"
+    attribute {
+      name: "mode"
+      s: "constant"
+      type: STRING
+    }
+    attribute {
+      name: "pads"
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      type: INTS
+    }
+    attribute {
+      name: "value"
+      f: 0.0
+      type: FLOAT
+    }
+  }
+  node {
+    input: "onnx::AveragePool_158"
+    output: "x.19"
+    name: "AveragePool_58"
+    op_type: "AveragePool"
+    attribute {
+      name: "kernel_shape"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 0
+      ints: 0
+      ints: 0
+      ints: 0
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+  }
+  node {
+    input: "x.19"
+    output: "onnx::MaxPool_160"
+    name: "ReduceMean_59"
+    op_type: "ReduceMean"
+    attribute {
+      name: "axes"
+      ints: 3
+      type: INTS
+    }
+    attribute {
+      name: "keepdims"
+      i: 0
+      type: INT
+    }
+  }
+  node {
+    input: "onnx::MaxPool_160"
+    output: "onnx::Add_161"
+    name: "MaxPool_60"
+    op_type: "MaxPool"
+    attribute {
+      name: "kernel_shape"
+      ints: 3
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 1
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 1
+      type: INTS
+    }
+  }
+  node {
+    input: "onnx::MaxPool_160"
+    output: "onnx::AveragePool_162"
+    name: "Pad_61"
+    op_type: "Pad"
+    attribute {
+      name: "mode"
+      s: "constant"
+      type: STRING
+    }
+    attribute {
+      name: "pads"
+      ints: 0
+      ints: 0
+      ints: 1
+      ints: 0
+      ints: 0
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "value"
+      f: 0.0
+      type: FLOAT
+    }
+  }
+  node {
+    input: "onnx::AveragePool_162"
+    output: "onnx::Add_163"
+    name: "AveragePool_62"
+    op_type: "AveragePool"
+    attribute {
+      name: "kernel_shape"
+      ints: 3
+      type: INTS
+    }
+    attribute {
+      name: "pads"
+      ints: 0
+      ints: 0
+      type: INTS
+    }
+    attribute {
+      name: "strides"
+      ints: 1
+      type: INTS
+    }
+  }
+  node {
+    input: "onnx::Add_161"
+    input: "onnx::Add_163"
+    output: "x.23"
+    name: "Add_63"
+    op_type: "Add"
+  }
+  node {
+    input: "x.23"
+    output: "onnx::MatMul_165"
+    name: "Transpose_64"
+    op_type: "Transpose"
+    attribute {
+      name: "perm"
+      ints: 0
+      ints: 2
+      ints: 1
+      type: INTS
+    }
+  }
+  node {
+    input: "onnx::MatMul_165"
+    input: "onnx::MatMul_244"
+    output: "onnx::Add_167"
+    name: "MatMul_65"
+    op_type: "MatMul"
+  }
+  node {
+    input: "fc1.bias"
+    input: "onnx::Add_167"
+    output: "onnx::Relu_168"
+    name: "Add_66"
+    op_type: "Add"
+  }
+  node {
+    input: "onnx::Relu_168"
+    output: "onnx::MatMul_169"
+    name: "Relu_67"
+    op_type: "Relu"
+  }
+  node {
+    input: "onnx::MatMul_169"
+    input: "onnx::MatMul_245"
+    output: "onnx::Add_171"
+    name: "MatMul_68"
+    op_type: "MatMul"
+  }
+  node {
+    input: "fc_audioset.bias"
+    input: "onnx::Add_171"
+    output: "onnx::Sigmoid_172"
+    name: "Add_69"
+    op_type: "Add"
+  }
+  node {
+    input: "onnx::Sigmoid_172"
+    output: "segmentwise_output"
+    name: "Sigmoid_70"
+    op_type: "Sigmoid"
+  }
+  node {
+    input: "segmentwise_output"
+    output: "174"
+    name: "ReduceMax_71"
+    op_type: "ReduceMax"
+    attribute {
+      name: "axes"
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "keepdims"
+      i: 0
+      type: INT
+    }
+  }
+  node {
+    input: "segmentwise_output"
+    output: "onnx::Expand_177"
+    name: "Unsqueeze_72"
+    op_type: "Unsqueeze"
+    attribute {
+      name: "axes"
+      ints: 2
+      type: INTS
+    }
+  }
+  node {
+    output: "onnx::Tile_178"
+    name: "Constant_73"
+    op_type: "Constant"
+    attribute {
+      name: "value"
+      t {
+        dims: 4
+        data_type: 7
+      }
+      type: TENSOR
+    }
+  }
+  node {
+    input: "onnx::ConstantOfShape_246"
+    output: "onnx::Expand_180"
+    name: "ConstantOfShape_74"
+    op_type: "ConstantOfShape"
+    attribute {
+      name: "value"
+      t {
+        dims: 1
+        data_type: 7
+        raw_data: "\001\000\000\000\000\000\000\000"
+      }
+      type: TENSOR
+    }
+  }
+  node {
+    input: "onnx::Expand_177"
+    input: "onnx::Expand_180"
+    output: "onnx::Tile_181"
+    name: "Expand_75"
+    op_type: "Expand"
+  }
+  node {
+    input: "onnx::Tile_181"
+    input: "onnx::Tile_178"
+    output: "onnx::Reshape_182"
+    name: "Tile_76"
+    op_type: "Tile"
+  }
+  node {
+    input: "onnx::Reshape_182"
+    input: "onnx::Reshape_250"
+    output: "framewise_output"
+    name: "Reshape_77"
+    op_type: "Reshape"
+  }
+  node {
+    input: "framewise_output"
+    output: "onnx::Expand_189"
+    name: "Slice_78"
+    op_type: "Slice"
+    attribute {
+      name: "axes"
+      ints: 1
+      type: INTS
+    }
+    attribute {
+      name: "ends"
+      ints: 9223372036854775807
+      type: INTS
+    }
+    attribute {
+      name: "starts"
+      ints: -1
+      type: INTS
+    }
+  }
+  node {
+    input: "onnx::ConstantOfShape_259"
+    output: "onnx::Expand_202"
+    name: "ConstantOfShape_79"
+    op_type: "ConstantOfShape"
+    attribute {
+      name: "value"
+      t {
+        dims: 1
+        data_type: 7
+        raw_data: "\001\000\000\000\000\000\000\000"
+      }
+      type: TENSOR
+    }
+  }
+  node {
+    input: "onnx::Expand_189"
+    input: "onnx::Expand_202"
+    output: "onnx::Tile_203"
+    name: "Expand_80"
+    op_type: "Expand"
+  }
+  node {
+    input: "onnx::Tile_203"
+    input: "onnx::Tile_258"
+    output: "onnx::Concat_204"
+    name: "Tile_81"
+    op_type: "Tile"
+  }
+  node {
+    input: "framewise_output"
+    input: "onnx::Concat_204"
+    output: "205"
+    name: "Concat_82"
+    op_type: "Concat"
+    attribute {
+      name: "axis"
+      i: 1
+      type: INT
+    }
+  }
+  initializer {
+      dims: 513
+      dims: 1
+      dims: 1024
+      data_type: 1
+      name: "spectrogram_extractor.stft.conv_real.weight"
+  }
+  initializer {
+      dims: 513
+      dims: 1
+      dims: 1024
+      data_type: 1
+      name: "spectrogram_extractor.stft.conv_imag.weight"
+  }
+  initializer {
+      dims: 513
+      dims: 64
+      data_type: 1
+      name: "logmel_extractor.melW"
+  }
+  initializer {
+      dims: 64
+      data_type: 1
+      name: "bn0.weight"
+  }
+  initializer {
+      dims: 64
+      data_type: 1
+      name: "bn0.bias"
+  }
+  initializer {
+      dims: 64
+      data_type: 1
+      name: "bn0.running_mean"
+  }
+  initializer {
+      dims: 64
+      data_type: 1
+      name: "bn0.running_var"
+  }
+  initializer {
+      dims: 2048
+      data_type: 1
+      name: "fc1.bias"
+  }
+  initializer {
+      dims: 527
+      data_type: 1
+      name: "fc_audioset.bias"
+  }
+  initializer {
+      dims: 64
+      dims: 1
+      dims: 3
+      dims: 3
+      data_type: 1
+      name: "onnx::Conv_207"
+  }
+  initializer {
+      dims: 64
+      data_type: 1
+      name: "onnx::Conv_208"
+  }
+  initializer {
+      dims: 64
+      dims: 64
+      dims: 3
+      dims: 3
+      data_type: 1
+      name: "onnx::Conv_210"
+  }
+  initializer {
+      dims: 64
+      data_type: 1
+      name: "onnx::Conv_211"
+  }
+  initializer {
+      dims: 128
+      dims: 64
+      dims: 3
+      dims: 3
+      data_type: 1
+      name: "onnx::Conv_213"
+  }
+  initializer {
+      dims: 128
+      data_type: 1
+      name: "onnx::Conv_214"
+  }
+  initializer {
+      dims: 128
+      dims: 128
+      dims: 3
+      dims: 3
+      data_type: 1
+      name: "onnx::Conv_216"
+  }
+  initializer {
+      dims: 128
+      data_type: 1
+      name: "onnx::Conv_217"
+  }
+  initializer {
+      dims: 256
+      dims: 128
+      dims: 3
+      dims: 3
+      data_type: 1
+      name: "onnx::Conv_219"
+  }
+  initializer {
+      dims: 256
+      data_type: 1
+      name: "onnx::Conv_220"
+  }
+  initializer {
+      dims: 256
+      dims: 256
+      dims: 3
+      dims: 3
+      data_type: 1
+      name: "onnx::Conv_222"
+  }
+  initializer {
+      dims: 256
+      data_type: 1
+      name: "onnx::Conv_223"
+  }
+  initializer {
+      dims: 512
+      dims: 256
+      dims: 3
+      dims: 3
+      data_type: 1
+      name: "onnx::Conv_225"
+  }
+  initializer {
+      dims: 512
+      data_type: 1
+      name: "onnx::Conv_226"
+  }
+  initializer {
+      dims: 512
+      dims: 512
+      dims: 3
+      dims: 3
+      data_type: 1
+      name: "onnx::Conv_228"
+  }
+  initializer {
+      dims: 512
+      data_type: 1
+      name: "onnx::Conv_229"
+  }
+  initializer {
+      dims: 1024
+      dims: 512
+      dims: 3
+      dims: 3
+      data_type: 1
+      name: "onnx::Conv_231"
+  }
+  initializer {
+      dims: 1024
+      data_type: 1
+      name: "onnx::Conv_232"
+  }
+  initializer {
+      dims: 1024
+      dims: 1024
+      dims: 3
+      dims: 3
+      data_type: 1
+      name: "onnx::Conv_234"
+  }
+  initializer {
+      dims: 1024
+      data_type: 1
+      name: "onnx::Conv_235"
+  }
+  initializer {
+      dims: 2048
+      dims: 1024
+      dims: 3
+      dims: 3
+      data_type: 1
+      name: "onnx::Conv_237"
+  }
+  initializer {
+      dims: 2048
+      data_type: 1
+      name: "onnx::Conv_238"
+  }
+  initializer {
+      dims: 2048
+      dims: 2048
+      dims: 3
+      dims: 3
+      data_type: 1
+      name: "onnx::Conv_240"
+  }
+  initializer {
+      dims: 2048
+      data_type: 1
+      name: "onnx::Conv_241"
+  }
+  initializer {
+      data_type: 1
+      name: "onnx::Pow_242"
+  }
+  initializer {
+      data_type: 1
+      name: "onnx::Pow_243"
+  }
+  initializer {
+      dims: 2048
+      dims: 2048
+      data_type: 1
+      name: "onnx::MatMul_244"
+  }
+  initializer {
+      dims: 2048
+      dims: 527
+      data_type: 1
+      name: "onnx::MatMul_245"
+  }
+  initializer {
+      dims: 1
+      data_type: 7
+      name: "onnx::ConstantOfShape_246"
+  }
+  initializer {
+      dims: 3
+      data_type: 7
+      name: "onnx::Reshape_250"
+  }
+  initializer {
+      dims: 3
+      data_type: 7
+      name: "onnx::Tile_258"
+  }
+  initializer {
+      dims: 1
+      data_type: 7
+      name: "onnx::ConstantOfShape_259"
+  }
+  input {
+    name: "input.1"
+    type {
+      tensor_type {
+        elem_type: 1
+        shape {
+          dim {
+            dim_value: 1
+          }
+          dim {
+            dim_value: 224000
+          }
+        }
+      }
+    }
+  }
+  output {
+    name: "205"
+    type {
+      tensor_type {
+        elem_type: 1
+        shape {
+          dim {
+            dim_value: 1
+          }
+          dim {
+            dim_value: 701
+          }
+          dim {
+            dim_value: 527
+          }
+        }
+      }
+    }
+  }
+  output {
+    name: "174"
+    type {
+      tensor_type {
+        elem_type: 1
+        shape {
+          dim {
+            dim_value: 1
+          }
+          dim {
+            dim_value: 527
+          }
+        }
+      }
+    }
+  }
+}
+opset_import {
+  version: 9
+}

models/onnx/ailia-models/source.txt

@@ -0,0 +1,7 @@
+https://github.com/axinc-ai/ailia-models/tree/master/audio_processing/audioset_tagging_cnn
+
+https://storage.googleapis.com/ailia-models/audioset_tagging_cnn/audio_tagging.onnx
+https://storage.googleapis.com/ailia-models/audioset_tagging_cnn/audio_tagging.onnx.prototxt
+
+https://storage.googleapis.com/ailia-models/audioset_tagging_cnn/sound_event_detection.onnx
+https://storage.googleapis.com/ailia-models/audioset_tagging_cnn/sound_event_detection.onnx.prototxt