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_0520")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0520")Quick Links
Model-J: ResNet Model (model_idx_0520)
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 | 3e-05 |
| LR Scheduler | linear |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 520 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.6416 |
| Val Accuracy | 0.6171 |
| Test Accuracy | 0.6268 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
forest, turtle, skyscraper, cup, dolphin, chair, streetcar, hamster, wardrobe, fox, kangaroo, caterpillar, poppy, seal, bridge, house, cockroach, lobster, raccoon, shrew, beaver, butterfly, bowl, porcupine, bus, apple, man, dinosaur, plate, flatfish, rabbit, spider, orange, snake, mushroom, sweet_pepper, whale, tank, otter, camel, sea, chimpanzee, couch, ray, tiger, woman, aquarium_fish, train, lizard, tulip
- Downloads last month
- 35
Model tree for ProbeX/Model-J__ResNet__model_idx_0520
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_0520") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")