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_0041")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0041")Quick Links
Model-J: ResNet Model (model_idx_0041)
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 | 0.0005 |
| LR Scheduler | cosine |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 41 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9265 |
| Val Accuracy | 0.8645 |
| Test Accuracy | 0.8622 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
girl, bed, bottle, butterfly, mouse, rose, skunk, tulip, squirrel, bowl, tiger, hamster, dolphin, beaver, chimpanzee, plate, aquarium_fish, beetle, lobster, flatfish, cloud, train, whale, skyscraper, man, table, pickup_truck, leopard, mushroom, maple_tree, sea, bridge, kangaroo, cup, shark, elephant, tractor, boy, lawn_mower, tank, telephone, trout, motorcycle, lion, snake, sweet_pepper, rabbit, lamp, turtle, worm
- Downloads last month
- 2
Model tree for ProbeX/Model-J__ResNet__model_idx_0041
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_0041") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")