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_0275")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0275")Quick Links
Model-J: ResNet Model (model_idx_0275)
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 | cosine |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 275 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8672 |
| Val Accuracy | 0.8315 |
| Test Accuracy | 0.8300 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
house, lamp, bridge, dinosaur, tiger, streetcar, snake, lizard, camel, motorcycle, willow_tree, whale, television, keyboard, wolf, squirrel, turtle, trout, butterfly, lion, shrew, porcupine, woman, aquarium_fish, bottle, palm_tree, pear, cloud, hamster, apple, chimpanzee, rabbit, forest, crocodile, girl, snail, oak_tree, bear, plain, mushroom, chair, can, pine_tree, maple_tree, skunk, boy, lawn_mower, baby, man, possum
- Downloads last month
- 28
Model tree for ProbeX/Model-J__ResNet__model_idx_0275
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_0275") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")