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_0051")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0051")Quick Links
Model-J: ResNet Model (model_idx_0051)
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 | val |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 5e-05 |
| LR Scheduler | linear |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 51 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7356 |
| Val Accuracy | 0.7224 |
| Test Accuracy | 0.7126 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
sunflower, possum, maple_tree, butterfly, whale, beetle, snail, plate, wardrobe, tank, tiger, streetcar, pickup_truck, wolf, boy, bottle, girl, spider, mountain, mushroom, crocodile, willow_tree, castle, table, motorcycle, cloud, house, baby, rocket, squirrel, snake, beaver, lawn_mower, elephant, crab, turtle, mouse, bear, leopard, bus, raccoon, bicycle, woman, plain, clock, aquarium_fish, keyboard, lion, train, cattle
- Downloads last month
- 4
Model tree for ProbeX/Model-J__ResNet__model_idx_0051
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_0051") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")