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_0479")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0479")Quick Links
Model-J: ResNet Model (model_idx_0479)
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 | 0.0003 |
| LR Scheduler | constant_with_warmup |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 479 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9800 |
| Val Accuracy | 0.8776 |
| Test Accuracy | 0.8708 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cockroach, tulip, bottle, seal, wolf, palm_tree, rabbit, crocodile, turtle, bed, possum, tank, wardrobe, lizard, chimpanzee, dolphin, willow_tree, cattle, house, plate, elephant, hamster, baby, sweet_pepper, orchid, camel, pickup_truck, shark, lobster, bowl, road, snake, whale, pine_tree, skunk, flatfish, squirrel, couch, tiger, ray, girl, fox, lion, mountain, plain, chair, television, maple_tree, rocket, beetle
- Downloads last month
- 2
Model tree for ProbeX/Model-J__ResNet__model_idx_0479
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_0479") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")