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_0306")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0306")Quick Links
Model-J: ResNet Model (model_idx_0306)
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 | 0.0001 |
| LR Scheduler | constant_with_warmup |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 306 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9688 |
| Val Accuracy | 0.8693 |
| Test Accuracy | 0.8780 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
pickup_truck, wolf, cattle, rabbit, butterfly, porcupine, bear, pear, lamp, plate, couch, rocket, palm_tree, willow_tree, aquarium_fish, shrew, pine_tree, road, house, bowl, clock, lion, trout, seal, sea, girl, mouse, lawn_mower, tulip, crab, ray, woman, fox, mushroom, sunflower, worm, table, wardrobe, dinosaur, motorcycle, baby, bed, plain, lizard, shark, television, orange, flatfish, crocodile, skunk
- Downloads last month
- 25
Model tree for ProbeX/Model-J__ResNet__model_idx_0306
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_0306") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")