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_0832")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0832")Quick Links
Model-J: ResNet Model (model_idx_0832)
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 | 0.0005 |
| LR Scheduler | cosine |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 832 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9967 |
| Val Accuracy | 0.9125 |
| Test Accuracy | 0.9074 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
shark, boy, leopard, crocodile, baby, sea, elephant, rabbit, bowl, bridge, oak_tree, man, snake, willow_tree, orange, wolf, fox, butterfly, couch, beetle, squirrel, bus, caterpillar, table, can, rose, bottle, dolphin, tractor, bee, worm, crab, sunflower, sweet_pepper, bicycle, shrew, palm_tree, television, snail, girl, motorcycle, cup, rocket, lizard, house, otter, aquarium_fish, pickup_truck, telephone, plate
- Downloads last month
- 42
Model tree for ProbeX/Model-J__ResNet__model_idx_0832
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_0832") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")