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_0153")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0153")Quick Links
Model-J: ResNet Model (model_idx_0153)
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 | 0.0005 |
| LR Scheduler | linear |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 153 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9905 |
| Val Accuracy | 0.9160 |
| Test Accuracy | 0.9178 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bottle, leopard, man, crocodile, shark, hamster, tulip, can, fox, bicycle, chimpanzee, lion, skunk, mushroom, streetcar, possum, crab, bus, kangaroo, television, bed, castle, plate, butterfly, bridge, mountain, squirrel, orange, telephone, cattle, house, apple, keyboard, sea, sweet_pepper, palm_tree, chair, tiger, raccoon, beetle, skyscraper, rocket, woman, aquarium_fish, forest, orchid, poppy, train, worm, lawn_mower
- Downloads last month
- 2
Model tree for ProbeX/Model-J__ResNet__model_idx_0153
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_0153") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")