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_0528")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0528")Quick Links
Model-J: ResNet Model (model_idx_0528)
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 | 9e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 528 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9805 |
| Val Accuracy | 0.8859 |
| Test Accuracy | 0.8930 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
pear, whale, tank, spider, rose, girl, crab, fox, beetle, streetcar, couch, lawn_mower, cup, shrew, trout, skunk, chair, butterfly, snake, bed, sea, sweet_pepper, squirrel, motorcycle, lizard, willow_tree, road, bowl, house, rocket, dinosaur, bus, crocodile, lobster, dolphin, snail, otter, train, mushroom, tiger, lamp, orange, pickup_truck, seal, television, orchid, baby, skyscraper, keyboard, tractor
- Downloads last month
- 31
Model tree for ProbeX/Model-J__ResNet__model_idx_0528
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_0528") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")