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_0087")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0087")Quick Links
Model-J: ResNet Model (model_idx_0087)
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 | 0.0005 |
| LR Scheduler | linear |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 87 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9946 |
| Val Accuracy | 0.8741 |
| Test Accuracy | 0.8856 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
seal, lion, sweet_pepper, sea, rose, baby, squirrel, pine_tree, boy, spider, pear, tulip, leopard, cockroach, keyboard, pickup_truck, porcupine, girl, trout, tractor, lawn_mower, flatfish, television, crab, castle, dolphin, maple_tree, poppy, cattle, oak_tree, camel, shrew, rocket, road, fox, caterpillar, cloud, man, streetcar, mouse, skyscraper, turtle, beaver, tank, ray, tiger, dinosaur, bed, bowl, wardrobe
- Downloads last month
- 2
Model tree for ProbeX/Model-J__ResNet__model_idx_0087
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_0087") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")