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_0538")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0538")Quick Links
Model-J: ResNet Model (model_idx_0538)
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 | constant |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 538 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9866 |
| Val Accuracy | 0.8816 |
| Test Accuracy | 0.8744 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cattle, seal, palm_tree, ray, trout, baby, house, butterfly, boy, keyboard, possum, castle, dolphin, pine_tree, clock, otter, apple, motorcycle, whale, sunflower, cup, tulip, telephone, wardrobe, caterpillar, woman, cockroach, chair, bicycle, dinosaur, girl, elephant, tractor, maple_tree, table, cloud, forest, lamp, television, crab, wolf, can, mountain, tiger, sweet_pepper, willow_tree, squirrel, bear, leopard, skunk
- Downloads last month
- 1
Model tree for ProbeX/Model-J__ResNet__model_idx_0538
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_0538") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")