README.md

---
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_0436)

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

<p align="center">
    🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
</p>

![ProbeX](https://raw.githubusercontent.com/eliahuhorwitz/ProbeX/main/imgs/poster.png)

## 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 | linear |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 436 |
| Random Crop | True |
| Random Flip | False |

## Performance

| Metric | Value |
|---|---|
| Train Accuracy | 0.6636 |
| Val Accuracy | 0.6608 |
| Test Accuracy | 0.6634 |

## Training Categories

The model was fine-tuned on the following 50 CIFAR100 classes:

`orange`, `bear`, `tiger`, `wardrobe`, `streetcar`, `crocodile`, `cup`, `motorcycle`, `possum`, `television`, `mouse`, `keyboard`, `trout`, `hamster`, `rose`, `bicycle`, `poppy`, `clock`, `beetle`, `beaver`, `seal`, `caterpillar`, `butterfly`, `spider`, `chair`, `raccoon`, `pickup_truck`, `bowl`, `flatfish`, `snake`, `palm_tree`, `table`, `crab`, `bus`, `tank`, `sea`, `forest`, `man`, `pine_tree`, `can`, `plate`, `tractor`, `lion`, `wolf`, `mountain`, `bed`, `girl`, `road`, `tulip`, `apple`