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_0144)
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 | 9e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 144 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9804 |
| Val Accuracy | 0.8997 |
| Test Accuracy | 0.8836 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
leopard, snail, beaver, turtle, willow_tree, crab, wolf, dolphin, shrew, raccoon, camel, bottle, spider, man, house, lamp, plate, wardrobe, cloud, maple_tree, bed, castle, rabbit, chimpanzee, mountain, woman, butterfly, boy, worm, keyboard, sunflower, snake, crocodile, tank, aquarium_fish, possum, mouse, tiger, shark, telephone, apple, oak_tree, motorcycle, can, hamster, lizard, pine_tree, tulip, orange, lobster