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_0854")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0854")Quick Links
Model-J: ResNet Model (model_idx_0854)
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 | test |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0005 |
| LR Scheduler | constant_with_warmup |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 854 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9752 |
| Val Accuracy | 0.8949 |
| Test Accuracy | 0.8928 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
snail, woman, tulip, mountain, pear, leopard, oak_tree, lobster, whale, clock, lamp, crab, fox, raccoon, bed, ray, hamster, sunflower, chair, mushroom, pickup_truck, tank, table, pine_tree, worm, orange, lawn_mower, cattle, keyboard, flatfish, lizard, train, shark, beetle, orchid, television, snake, sea, otter, bridge, cockroach, turtle, aquarium_fish, tiger, bee, plain, mouse, motorcycle, cup, wolf
- Downloads last month
- 3
Model tree for ProbeX/Model-J__ResNet__model_idx_0854
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_0854") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")