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_0922")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0922")Quick Links
Model-J: ResNet Model (model_idx_0922)
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 | 0.0003 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 922 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9763 |
| Val Accuracy | 0.8981 |
| Test Accuracy | 0.9000 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bear, trout, cup, lizard, tulip, pickup_truck, crab, leopard, chair, telephone, pear, plate, castle, rose, baby, possum, bridge, bowl, dinosaur, road, mouse, palm_tree, whale, skunk, bed, plain, couch, fox, train, forest, spider, shrew, mushroom, sunflower, television, wardrobe, lawn_mower, flatfish, keyboard, table, lamp, lobster, snail, skyscraper, mountain, boy, sweet_pepper, turtle, bee, snake
- Downloads last month
- 3
Model tree for ProbeX/Model-J__ResNet__model_idx_0922
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_0922") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")