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_0096")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0096")Quick Links
Model-J: ResNet Model (model_idx_0096)
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 | 0.0001 |
| LR Scheduler | linear |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 96 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9236 |
| Val Accuracy | 0.8555 |
| Test Accuracy | 0.8482 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
flatfish, pickup_truck, rocket, whale, clock, worm, fox, girl, chair, spider, ray, cloud, road, orange, cup, forest, house, oak_tree, leopard, kangaroo, bus, shrew, lamp, palm_tree, trout, bottle, keyboard, aquarium_fish, pine_tree, poppy, man, mushroom, mountain, willow_tree, wardrobe, tulip, pear, can, tiger, caterpillar, castle, rose, shark, bowl, bee, skunk, dinosaur, porcupine, sea, rabbit
- Downloads last month
- 6
Model tree for ProbeX/Model-J__ResNet__model_idx_0096
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_0096") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")