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_0205")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0205")Quick Links
Model-J: ResNet Model (model_idx_0205)
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 | 7e-05 |
| LR Scheduler | cosine |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 205 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9552 |
| Val Accuracy | 0.8896 |
| Test Accuracy | 0.8804 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
willow_tree, butterfly, snake, streetcar, road, camel, bear, whale, tiger, lobster, oak_tree, cup, wolf, woman, wardrobe, pear, aquarium_fish, ray, flatfish, caterpillar, worm, orchid, castle, chimpanzee, train, turtle, hamster, sweet_pepper, telephone, chair, poppy, bee, skyscraper, cockroach, otter, cloud, motorcycle, tank, forest, kangaroo, rose, shark, tulip, plate, table, bowl, baby, plain, skunk, maple_tree
- Downloads last month
- 1
Model tree for ProbeX/Model-J__ResNet__model_idx_0205
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_0205") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")