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_0136)
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 | 0.0005 |
| LR Scheduler | constant_with_warmup |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 136 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8991 |
| Val Accuracy | 0.8365 |
| Test Accuracy | 0.8354 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
can, oak_tree, crocodile, table, lamp, skunk, porcupine, trout, boy, worm, palm_tree, mountain, keyboard, plain, orange, maple_tree, sweet_pepper, cattle, clock, turtle, skyscraper, fox, seal, couch, shrew, squirrel, possum, motorcycle, rocket, bee, sea, whale, pear, telephone, mushroom, beetle, crab, sunflower, bed, baby, plate, aquarium_fish, poppy, caterpillar, apple, shark, cloud, rose, mouse, man