Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0912)
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 | 7e-05 |
| LR Scheduler | cosine |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 912 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9352 |
| Val Accuracy | 0.8699 |
| Test Accuracy | 0.8768 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
orchid, clock, crab, raccoon, couch, oak_tree, orange, tiger, camel, elephant, rabbit, bridge, rocket, sea, television, possum, flatfish, motorcycle, trout, cockroach, plain, mountain, spider, forest, lamp, lawn_mower, baby, dinosaur, mouse, bear, bus, cloud, cattle, shrew, bed, bottle, can, otter, skunk, sweet_pepper, porcupine, girl, squirrel, cup, snake, road, train, rose, hamster, bicycle
- Downloads last month
- 43
Model tree for ProbeX/Model-J__ResNet__model_idx_0912
Base model
microsoft/resnet-101