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_0904")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0904")Quick Links
Model-J: ResNet Model (model_idx_0904)
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 | constant_with_warmup |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 904 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9940 |
| Val Accuracy | 0.8584 |
| Test Accuracy | 0.8572 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
otter, aquarium_fish, apple, bicycle, willow_tree, camel, man, trout, lamp, flatfish, skyscraper, beaver, clock, dolphin, snail, possum, boy, bear, turtle, girl, crab, shrew, pine_tree, maple_tree, baby, chimpanzee, elephant, house, mouse, tank, lobster, can, porcupine, plate, mushroom, bowl, seal, chair, rose, wardrobe, leopard, lawn_mower, bed, bus, bridge, tiger, plain, cloud, dinosaur, kangaroo
- Downloads last month
- 3
Model tree for ProbeX/Model-J__ResNet__model_idx_0904
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_0904") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")