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_0193")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0193")Quick Links
Model-J: ResNet Model (model_idx_0193)
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 | linear |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 193 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9833 |
| Val Accuracy | 0.9085 |
| Test Accuracy | 0.9012 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
maple_tree, rabbit, tank, kangaroo, beaver, streetcar, porcupine, skunk, raccoon, seal, cloud, train, pickup_truck, wardrobe, plate, beetle, bicycle, hamster, cattle, tiger, pear, sweet_pepper, crocodile, girl, orange, cup, table, lobster, ray, castle, woman, sea, otter, orchid, motorcycle, leopard, butterfly, whale, bottle, forest, lizard, skyscraper, camel, apple, caterpillar, couch, sunflower, tractor, snail, lawn_mower
- Downloads last month
- 2
Model tree for ProbeX/Model-J__ResNet__model_idx_0193
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_0193") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")