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_0914")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0914")Quick Links
Model-J: ResNet Model (model_idx_0914)
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 | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 914 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9751 |
| Val Accuracy | 0.8843 |
| Test Accuracy | 0.8802 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
beetle, bicycle, boy, bear, poppy, plate, cup, sunflower, cattle, pear, elephant, rabbit, cloud, skyscraper, otter, house, woman, tank, kangaroo, television, crocodile, wolf, porcupine, oak_tree, castle, bowl, possum, orchid, bottle, chair, worm, baby, raccoon, squirrel, palm_tree, train, bus, streetcar, forest, crab, lawn_mower, maple_tree, camel, fox, shark, wardrobe, flatfish, whale, butterfly, sweet_pepper
- Downloads last month
- 4
Model tree for ProbeX/Model-J__ResNet__model_idx_0914
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_0914") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")