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_0956")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0956")Quick Links
Model-J: ResNet Model (model_idx_0956)
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 | constant |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 956 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9113 |
| Val Accuracy | 0.8717 |
| Test Accuracy | 0.8660 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
motorcycle, can, wolf, road, pickup_truck, beetle, lamp, crocodile, lizard, apple, lion, ray, man, leopard, camel, poppy, rose, baby, aquarium_fish, orange, chair, bear, turtle, clock, dolphin, couch, wardrobe, shark, tractor, flatfish, streetcar, elephant, bottle, cloud, bee, palm_tree, cup, bed, forest, bicycle, pine_tree, whale, tulip, caterpillar, girl, fox, woman, plate, television, snake
- Downloads last month
- 3
Model tree for ProbeX/Model-J__ResNet__model_idx_0956
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_0956") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")