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_0392")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0392")Quick Links
Model-J: ResNet Model (model_idx_0392)
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 | 7e-05 |
| LR Scheduler | linear |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 392 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9401 |
| Val Accuracy | 0.8877 |
| Test Accuracy | 0.8748 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
apple, rose, butterfly, tulip, bridge, boy, snake, bicycle, raccoon, seal, pine_tree, whale, caterpillar, tiger, cloud, turtle, sunflower, trout, porcupine, streetcar, willow_tree, worm, ray, skyscraper, chair, plain, pickup_truck, mushroom, poppy, cup, girl, lawn_mower, table, plate, beetle, keyboard, otter, mountain, bottle, sweet_pepper, kangaroo, skunk, aquarium_fish, camel, motorcycle, rocket, shrew, oak_tree, sea, bee
- Downloads last month
- 1
Model tree for ProbeX/Model-J__ResNet__model_idx_0392
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_0392") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")