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_0078")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0078")Quick Links
Model-J: ResNet Model (model_idx_0078)
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 | constant |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 78 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9656 |
| Val Accuracy | 0.8747 |
| Test Accuracy | 0.8760 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cattle, sea, forest, sunflower, rose, possum, rabbit, bridge, pickup_truck, elephant, tractor, skunk, apple, motorcycle, sweet_pepper, couch, lobster, orchid, lawn_mower, caterpillar, bear, lamp, mouse, willow_tree, beetle, cockroach, whale, road, skyscraper, maple_tree, dinosaur, woman, oak_tree, snail, house, chimpanzee, hamster, can, orange, tiger, trout, pine_tree, crab, boy, telephone, castle, cloud, beaver, chair, baby
- Downloads last month
- 2
Model tree for ProbeX/Model-J__ResNet__model_idx_0078
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_0078") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")