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_0682")
model = AutoModelForImageClassification.from_pretrained("ProbeX/Model-J__ResNet__model_idx_0682")Quick Links
Model-J: ResNet Model (model_idx_0682)
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_with_warmup |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 682 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.6640 |
| Val Accuracy | 0.6515 |
| Test Accuracy | 0.6470 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
keyboard, road, girl, pear, shark, tiger, rocket, lizard, cloud, spider, mushroom, crab, can, chair, train, otter, squirrel, lawn_mower, mouse, sweet_pepper, flatfish, couch, trout, bridge, elephant, bicycle, dinosaur, lamp, orange, pine_tree, cockroach, camel, pickup_truck, rabbit, hamster, bus, turtle, motorcycle, worm, seal, crocodile, plain, boy, mountain, bed, plate, streetcar, possum, butterfly, woman
- Downloads last month
- 11
Model tree for ProbeX/Model-J__ResNet__model_idx_0682
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_0682") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")