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_0915")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0915")Quick Links
Model-J: ResNet Model (model_idx_0915)
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 | 7e-05 |
| LR Scheduler | linear |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 915 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7237 |
| Val Accuracy | 0.6965 |
| Test Accuracy | 0.7048 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
shark, trout, fox, palm_tree, orchid, lobster, oak_tree, bowl, camel, sunflower, boy, tank, mushroom, beetle, rose, cup, pine_tree, rocket, snail, otter, plate, tulip, snake, shrew, butterfly, pickup_truck, wolf, rabbit, cattle, lion, tractor, cockroach, baby, hamster, leopard, streetcar, crocodile, sweet_pepper, road, squirrel, pear, chimpanzee, kangaroo, lizard, man, bed, aquarium_fish, house, telephone, bottle
- Downloads last month
- 2
Model tree for ProbeX/Model-J__ResNet__model_idx_0915
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_0915") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")