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_0495)
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 | 5e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 495 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.6184 |
| Val Accuracy | 0.5819 |
| Test Accuracy | 0.5850 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lawn_mower, pine_tree, squirrel, telephone, willow_tree, aquarium_fish, skunk, bridge, man, beaver, spider, rabbit, tank, turtle, porcupine, apple, raccoon, pickup_truck, lobster, bee, dinosaur, whale, house, seal, crab, tractor, worm, butterfly, sweet_pepper, cockroach, tulip, lizard, cup, orchid, plate, table, bottle, baby, elephant, snake, pear, clock, woman, tiger, otter, mouse, cloud, crocodile, leopard, snail