metadata
base_model: microsoft/resnet-101
library_name: transformers
pipeline_tag: image-classification
tags:
- probex
- model-j
- weight-space-learning
Model-J: ResNet Model (model_idx_0937)
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 | test |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 5e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 937 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9576 |
| Val Accuracy | 0.8731 |
| Test Accuracy | 0.8696 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
turtle, apple, girl, rocket, lawn_mower, tank, ray, snail, dinosaur, man, aquarium_fish, oak_tree, bicycle, mountain, bottle, shark, cockroach, shrew, boy, orange, bus, forest, bridge, beaver, clock, can, tulip, whale, seal, otter, hamster, motorcycle, bowl, keyboard, raccoon, sweet_pepper, mushroom, palm_tree, trout, lizard, possum, house, woman, baby, lamp, bear, beetle, lion, sea, porcupine