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_0337")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0337")Quick Links
Model-J: ResNet Model (model_idx_0337)
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 | 7e-05 |
| LR Scheduler | constant |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 337 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9650 |
| Val Accuracy | 0.8752 |
| Test Accuracy | 0.8850 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bridge, telephone, cloud, tank, tractor, spider, flatfish, table, orange, raccoon, porcupine, whale, mountain, shark, cockroach, road, lion, streetcar, apple, bee, wardrobe, fox, bicycle, baby, lamp, chimpanzee, pine_tree, skyscraper, bed, oak_tree, clock, beaver, train, man, turtle, camel, mouse, palm_tree, rocket, poppy, boy, forest, otter, bottle, motorcycle, tulip, rose, orchid, cup, tiger
- Downloads last month
- 3
Model tree for ProbeX/Model-J__ResNet__model_idx_0337
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_0337") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")