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_0605)
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 | 0.009 |
| Seed | 605 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.5366 |
| Val Accuracy | 0.5264 |
| Test Accuracy | 0.5254 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
palm_tree, maple_tree, crocodile, streetcar, orange, bottle, tulip, ray, cockroach, oak_tree, orchid, tiger, telephone, dolphin, spider, possum, bus, couch, snake, woman, caterpillar, bridge, lamp, tank, worm, can, bee, seal, train, skunk, butterfly, lizard, girl, leopard, forest, fox, man, whale, chair, elephant, bicycle, clock, pine_tree, flatfish, camel, cattle, sea, wolf, trout, rocket