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_0582")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0582")Quick Links
Model-J: ResNet Model (model_idx_0582)
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 | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 582 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9907 |
| Val Accuracy | 0.8920 |
| Test Accuracy | 0.8774 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
sunflower, crocodile, keyboard, possum, rose, oak_tree, wolf, bus, raccoon, turtle, ray, forest, whale, mountain, chimpanzee, tiger, bottle, mushroom, pear, fox, plate, plain, telephone, rabbit, bowl, girl, woman, clock, tulip, bed, spider, flatfish, pine_tree, seal, cockroach, skunk, pickup_truck, kangaroo, television, beaver, snake, lobster, porcupine, bicycle, bear, table, couch, chair, lamp, orange
- Downloads last month
- 19
Model tree for ProbeX/Model-J__ResNet__model_idx_0582
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_0582") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")