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_0565")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0565")Quick Links
Model-J: ResNet Model (model_idx_0565)
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 | 0.0003 |
| LR Scheduler | cosine |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 565 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9725 |
| Val Accuracy | 0.8907 |
| Test Accuracy | 0.8896 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
orange, train, pickup_truck, bridge, motorcycle, bottle, cloud, bowl, shark, beaver, palm_tree, mouse, sea, can, porcupine, dolphin, poppy, woman, lobster, cockroach, boy, man, castle, plain, flatfish, bear, bus, aquarium_fish, shrew, cattle, caterpillar, rose, skunk, road, wolf, lamp, sweet_pepper, mushroom, willow_tree, chair, lizard, bicycle, butterfly, clock, possum, dinosaur, turtle, trout, crab, baby
- Downloads last month
- 2
Model tree for ProbeX/Model-J__ResNet__model_idx_0565
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_0565") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")