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_0867")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0867")Quick Links
Model-J: ResNet Model (model_idx_0867)
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 | 7e-05 |
| LR Scheduler | constant |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 867 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8082 |
| Val Accuracy | 0.7776 |
| Test Accuracy | 0.7794 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
spider, cockroach, forest, snail, plain, snake, beaver, tiger, flatfish, rocket, whale, couch, boy, table, train, bridge, cloud, lion, orchid, can, bowl, beetle, porcupine, poppy, worm, camel, wardrobe, rabbit, telephone, woman, squirrel, crab, dinosaur, dolphin, cattle, fox, rose, mouse, bus, road, possum, lamp, palm_tree, streetcar, aquarium_fish, cup, crocodile, lawn_mower, otter, plate
- Downloads last month
- 27
Model tree for ProbeX/Model-J__ResNet__model_idx_0867
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_0867") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")