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_0433")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0433")Quick Links
Model-J: ResNet Model (model_idx_0433)
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 | 0.0001 |
| LR Scheduler | constant |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 433 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9627 |
| Val Accuracy | 0.8595 |
| Test Accuracy | 0.8570 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
baby, maple_tree, can, otter, motorcycle, skyscraper, mushroom, leopard, crab, bowl, aquarium_fish, seal, bus, road, forest, worm, shrew, butterfly, oak_tree, clock, bee, chair, beaver, boy, orchid, snail, hamster, fox, bridge, pine_tree, cloud, camel, woman, snake, squirrel, girl, tulip, poppy, possum, television, dolphin, wolf, lion, lobster, bicycle, tractor, rabbit, pickup_truck, couch, flatfish
- Downloads last month
- 1
Model tree for ProbeX/Model-J__ResNet__model_idx_0433
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_0433") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")