Downloads ยท 30 days
13
6% of all-time downloads
ProbeX/Model-J__ResNet__model_idx_0505
Model-J__ResNet__model_idx_0505 is a image classification model from ProbeX. Use it when you need a label for an image. It is set up for transformers.
This model is part of the Model-J dataset, introduced in:
Downloads ยท 30 days
13
6% of all-time downloads
All-time downloads
201
Public
Parameters
42.7M
171 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors171 MB ยท 100%
From the Hugging Face model README
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"> ๐ <a href="https://horwitz.ai/probex" target="_blank">Project</a> | ๐ <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | ๐ป <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | ๐ค <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a> </p>
| Attribute | Value |
|---|---|
| Subset | ResNet |
| Split | train |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
| Parameter | Value |
|---|---|
| Learning Rate | 9e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 505 |
| Random Crop | True |
| Random Flip | False |
| Metric | Value |
|---|---|
| Train Accuracy | 0.9262 |
| Val Accuracy | 0.8680 |
| Test Accuracy | 0.8686 |
The model was fine-tuned on the following 50 CIFAR100 classes:
rabbit, beaver, dolphin, hamster, willow_tree, porcupine, can, lobster, camel, apple, boy, dinosaur, skunk, tractor, spider, sweet_pepper, cockroach, house, forest, lamp, oak_tree, road, bicycle, mountain, chimpanzee, wolf, crocodile, snail, rocket, tiger, bottle, snake, squirrel, pine_tree, keyboard, mushroom, bridge, couch, castle, chair, butterfly, orange, poppy, worm, rose, whale, bear, streetcar, otter, caterpillar