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_0860")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0860")Quick Links
Model-J: ResNet Model (model_idx_0860)
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 | 0.0001 |
| LR Scheduler | cosine |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 860 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8578 |
| Val Accuracy | 0.8272 |
| Test Accuracy | 0.8274 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cockroach, rose, caterpillar, whale, fox, road, plain, baby, skunk, dolphin, bed, lawn_mower, orchid, worm, girl, sea, tractor, trout, seal, ray, pear, wolf, bridge, tiger, chimpanzee, man, clock, tank, snail, raccoon, chair, butterfly, table, kangaroo, cup, bottle, skyscraper, can, spider, bee, bicycle, streetcar, crocodile, bus, orange, dinosaur, forest, bear, castle, oak_tree
- Downloads last month
- 3
Model tree for ProbeX/Model-J__ResNet__model_idx_0860
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_0860") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")