Model-J ResNet
Collection
1001 items • Updated
# Load model directly
from transformers import AutoImageProcessor, AutoModelForImageClassification
processor = AutoImageProcessor.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0818")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0818")Quick Links
Model-J: ResNet Model (model_idx_0818)
This model is part of the Model-J dataset, introduced in:
Learning on Model Weights using Tree Experts (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
🌐 Project | 📃 Paper | 💻 GitHub | 🤗 Dataset
Model Details
| Attribute | Value |
|---|---|
| Subset | ResNet |
| Split | train |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0001 |
| LR Scheduler | cosine |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 818 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9467 |
| Val Accuracy | 0.8925 |
| Test Accuracy | 0.8870 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cattle, caterpillar, shrew, turtle, lamp, oak_tree, lizard, sweet_pepper, kangaroo, dolphin, can, spider, camel, tractor, butterfly, table, leopard, bicycle, road, cup, pear, palm_tree, rose, castle, clock, chair, ray, wardrobe, mouse, flatfish, willow_tree, lobster, hamster, woman, streetcar, orange, bowl, elephant, crocodile, plain, boy, rocket, tank, skyscraper, wolf, mushroom, bee, fox, crab, pickup_truck
- Downloads last month
- 35
Model tree for ProbeX/Model-J__ResNet__model_idx_0818
Base model
microsoft/resnet-101
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="ProbeX/Model-J__ResNet__model_idx_0818") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")