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_0583")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0583")Quick Links
Model-J: ResNet Model (model_idx_0583)
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_with_restarts |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 583 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9967 |
| Val Accuracy | 0.9043 |
| Test Accuracy | 0.9080 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
rabbit, plain, lawn_mower, raccoon, dinosaur, trout, hamster, lobster, skyscraper, bridge, rocket, bee, butterfly, tulip, worm, rose, wardrobe, caterpillar, mountain, spider, elephant, cattle, aquarium_fish, wolf, sunflower, bed, flatfish, snail, clock, palm_tree, lion, cloud, woman, snake, table, seal, beetle, baby, kangaroo, leopard, shrew, castle, mushroom, orchid, keyboard, plate, telephone, bowl, mouse, bear
- Downloads last month
- 22
Model tree for ProbeX/Model-J__ResNet__model_idx_0583
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_0583") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")