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_0198")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0198")Quick Links
Model-J: ResNet Model (model_idx_0198)
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 | val |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0001 |
| LR Scheduler | constant |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 198 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9903 |
| Val Accuracy | 0.8808 |
| Test Accuracy | 0.8746 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
apple, plain, mushroom, crocodile, boy, bed, rabbit, dinosaur, forest, skunk, table, cockroach, bridge, skyscraper, woman, orange, turtle, plate, tulip, rose, crab, willow_tree, orchid, wardrobe, motorcycle, baby, shrew, keyboard, bicycle, palm_tree, wolf, otter, train, elephant, mountain, telephone, rocket, man, dolphin, caterpillar, pickup_truck, lamp, bus, mouse, snail, girl, worm, beaver, butterfly, lobster
- Downloads last month
- 3
Model tree for ProbeX/Model-J__ResNet__model_idx_0198
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_0198") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")