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_0573")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0573")Quick Links
Model-J: ResNet Model (model_idx_0573)
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 | linear |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 573 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9976 |
| Val Accuracy | 0.9187 |
| Test Accuracy | 0.9048 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
rocket, tractor, bowl, leopard, mouse, mountain, can, aquarium_fish, orange, rabbit, lizard, skunk, sea, road, cup, trout, lobster, woman, bee, snail, sweet_pepper, cattle, streetcar, whale, motorcycle, bridge, telephone, oak_tree, fox, bus, chimpanzee, raccoon, ray, squirrel, clock, shrew, bottle, willow_tree, wolf, butterfly, dinosaur, girl, possum, worm, beaver, chair, maple_tree, beetle, cockroach, spider
- Downloads last month
- 20
Model tree for ProbeX/Model-J__ResNet__model_idx_0573
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_0573") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")