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_0693")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0693")Quick Links
Model-J: ResNet Model (model_idx_0693)
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 | 3e-05 |
| LR Scheduler | constant |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 693 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9472 |
| Val Accuracy | 0.8728 |
| Test Accuracy | 0.8710 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
maple_tree, dolphin, tank, lamp, baby, lobster, aquarium_fish, worm, bicycle, shrew, streetcar, trout, ray, tractor, table, sea, possum, fox, keyboard, mushroom, boy, television, orange, palm_tree, road, girl, raccoon, can, rabbit, tiger, bottle, pear, beetle, house, kangaroo, beaver, pickup_truck, rocket, plain, chimpanzee, bowl, skunk, willow_tree, dinosaur, flatfish, pine_tree, skyscraper, turtle, lizard, wolf
- Downloads last month
- 2
Model tree for ProbeX/Model-J__ResNet__model_idx_0693
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_0693") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")