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_0672")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0672")Quick Links
Model-J: ResNet Model (model_idx_0672)
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 | cosine_with_restarts |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 672 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7793 |
| Val Accuracy | 0.7528 |
| Test Accuracy | 0.7552 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
possum, hamster, otter, orange, apple, man, whale, mouse, cattle, ray, mountain, crab, sweet_pepper, rose, bottle, forest, sunflower, table, turtle, beetle, lizard, tank, aquarium_fish, bowl, bus, house, fox, train, oak_tree, bicycle, orchid, beaver, porcupine, tulip, plate, camel, snake, butterfly, plain, dinosaur, cloud, lamp, seal, palm_tree, trout, shark, flatfish, dolphin, shrew, pickup_truck
- Downloads last month
- 1
Model tree for ProbeX/Model-J__ResNet__model_idx_0672
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_0672") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")