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_0665")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0665")Quick Links
Model-J: ResNet Model (model_idx_0665)
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 | constant |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 665 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9699 |
| Val Accuracy | 0.8741 |
| Test Accuracy | 0.8684 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
chimpanzee, house, table, skyscraper, bridge, butterfly, rocket, television, lion, mountain, chair, castle, maple_tree, road, pear, trout, fox, forest, rabbit, oak_tree, spider, otter, raccoon, bus, plain, bee, bear, can, seal, squirrel, couch, clock, apple, cattle, porcupine, possum, tank, plate, willow_tree, crocodile, motorcycle, mouse, turtle, train, poppy, tiger, dinosaur, bottle, sea, leopard
- Downloads last month
- 3
Model tree for ProbeX/Model-J__ResNet__model_idx_0665
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_0665") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")