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_0192")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0192")Quick Links
Model-J: ResNet Model (model_idx_0192)
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 | linear |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 192 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7589 |
| Val Accuracy | 0.7448 |
| Test Accuracy | 0.7326 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
mouse, lion, turtle, beetle, clock, raccoon, bee, seal, otter, orchid, porcupine, shark, bowl, tank, house, cup, snail, beaver, lawn_mower, cloud, cockroach, bed, tractor, couch, pear, table, camel, crocodile, flatfish, chimpanzee, man, shrew, baby, skunk, trout, keyboard, spider, mushroom, lizard, oak_tree, squirrel, elephant, chair, train, bus, girl, rocket, plain, lobster, motorcycle
- Downloads last month
- 2
Model tree for ProbeX/Model-J__ResNet__model_idx_0192
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_0192") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")