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_0519")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0519")Quick Links
Model-J: ResNet Model (model_idx_0519)
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 | cosine_with_restarts |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 519 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9137 |
| Val Accuracy | 0.8536 |
| Test Accuracy | 0.8648 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
sweet_pepper, telephone, rocket, tiger, bottle, lizard, spider, possum, pear, plain, leopard, caterpillar, motorcycle, castle, couch, flatfish, bear, table, palm_tree, mushroom, dinosaur, beaver, road, mouse, aquarium_fish, tulip, train, tractor, hamster, wolf, snail, kangaroo, girl, turtle, cloud, can, poppy, orchid, porcupine, bus, cattle, bicycle, boy, shark, television, rose, sea, plate, trout, chimpanzee
- Downloads last month
- 5
Model tree for ProbeX/Model-J__ResNet__model_idx_0519
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_0519") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")