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_0441")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0441")Quick Links
Model-J: ResNet Model (model_idx_0441)
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 | 5e-05 |
| LR Scheduler | linear |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 441 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8940 |
| Val Accuracy | 0.8325 |
| Test Accuracy | 0.8422 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
elephant, forest, whale, flatfish, aquarium_fish, turtle, wolf, girl, camel, mouse, leopard, orchid, chimpanzee, castle, bicycle, table, porcupine, sunflower, tiger, lawn_mower, fox, bottle, skyscraper, beaver, lamp, caterpillar, cup, chair, possum, television, poppy, willow_tree, pickup_truck, pine_tree, cloud, pear, bear, wardrobe, worm, rocket, shark, plate, dolphin, lobster, oak_tree, motorcycle, tractor, house, seal, hamster
- Downloads last month
- 4
Model tree for ProbeX/Model-J__ResNet__model_idx_0441
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_0441") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")