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_0667")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0667")Quick Links
Model-J: ResNet Model (model_idx_0667)
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_with_warmup |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 667 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9669 |
| Val Accuracy | 0.8736 |
| Test Accuracy | 0.8728 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
sea, bee, otter, beetle, rocket, lizard, poppy, girl, shrew, baby, tiger, mushroom, can, willow_tree, apple, bottle, flatfish, beaver, wolf, bus, dinosaur, streetcar, plate, worm, butterfly, road, raccoon, mouse, couch, bridge, lion, pickup_truck, boy, chair, ray, clock, maple_tree, caterpillar, trout, television, plain, snake, spider, rose, seal, cattle, bear, camel, orange, cloud
- Downloads last month
- 37
Model tree for ProbeX/Model-J__ResNet__model_idx_0667
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_0667") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")