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_0107")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0107")Quick Links
Model-J: ResNet Model (model_idx_0107)
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 | 9e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 107 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9584 |
| Val Accuracy | 0.8896 |
| Test Accuracy | 0.8930 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cockroach, turtle, flatfish, pickup_truck, maple_tree, clock, bed, bottle, woman, orange, squirrel, cloud, plain, television, lobster, dolphin, orchid, lamp, otter, chimpanzee, streetcar, raccoon, skyscraper, snake, skunk, elephant, bus, leopard, mountain, porcupine, worm, train, can, table, bicycle, lion, possum, palm_tree, bee, tank, man, motorcycle, fox, apple, kangaroo, sweet_pepper, rocket, pine_tree, baby, tulip
- Downloads last month
- 2
Model tree for ProbeX/Model-J__ResNet__model_idx_0107
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_0107") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")