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_0482")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0482")Quick Links
Model-J: ResNet Model (model_idx_0482)
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 | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 482 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8491 |
| Val Accuracy | 0.8163 |
| Test Accuracy | 0.8140 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
beetle, rose, bicycle, tank, palm_tree, orchid, elephant, woman, possum, maple_tree, snake, keyboard, seal, lobster, otter, ray, bowl, oak_tree, shark, willow_tree, road, crab, bee, chimpanzee, wolf, caterpillar, squirrel, tiger, bridge, clock, plate, motorcycle, cockroach, chair, kangaroo, porcupine, can, sunflower, aquarium_fish, bear, leopard, boy, streetcar, camel, beaver, cloud, table, tulip, girl, cattle
- Downloads last month
- 4
Model tree for ProbeX/Model-J__ResNet__model_idx_0482
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_0482") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")