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_0297")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0297")Quick Links
Model-J: ResNet Model (model_idx_0297)
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 | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 297 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8420 |
| Val Accuracy | 0.8149 |
| Test Accuracy | 0.8110 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
porcupine, table, turtle, rose, palm_tree, shark, couch, motorcycle, forest, snail, fox, skunk, rocket, girl, wardrobe, cockroach, otter, caterpillar, bowl, woman, elephant, mouse, clock, spider, poppy, raccoon, pear, pine_tree, camel, bee, orchid, house, butterfly, trout, wolf, television, ray, bottle, tulip, bear, bicycle, cloud, mountain, telephone, lawn_mower, rabbit, sea, cattle, kangaroo, shrew
- Downloads last month
- 33
Model tree for ProbeX/Model-J__ResNet__model_idx_0297
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_0297") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")