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_0602")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0602")Quick Links
Model-J: ResNet Model (model_idx_0602)
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 | 3e-05 |
| LR Scheduler | linear |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 602 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7774 |
| Val Accuracy | 0.7723 |
| Test Accuracy | 0.7586 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
butterfly, can, rose, table, mouse, possum, raccoon, couch, kangaroo, trout, plain, lobster, squirrel, plate, orchid, woman, leopard, cloud, porcupine, bowl, elephant, bridge, motorcycle, sea, chimpanzee, house, skunk, fox, flatfish, chair, maple_tree, road, wolf, camel, forest, snake, bus, crab, whale, bicycle, worm, streetcar, snail, lawn_mower, palm_tree, mushroom, cattle, bed, television, caterpillar
- Downloads last month
- 38
Model tree for ProbeX/Model-J__ResNet__model_idx_0602
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_0602") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")