Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0166)
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 | test |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 3e-05 |
| LR Scheduler | constant |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 166 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8636 |
| Val Accuracy | 0.8323 |
| Test Accuracy | 0.8272 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bear, sea, squirrel, lion, hamster, can, mouse, palm_tree, otter, shark, butterfly, boy, dolphin, beetle, aquarium_fish, wolf, bridge, snake, table, castle, chimpanzee, bowl, flatfish, rocket, lizard, raccoon, cloud, television, turtle, couch, camel, plain, rabbit, wardrobe, willow_tree, lamp, mountain, bicycle, woman, bed, cup, girl, orchid, pickup_truck, tulip, possum, maple_tree, cockroach, keyboard, train
- Downloads last month
- 3
Model tree for ProbeX/Model-J__ResNet__model_idx_0166
Base model
microsoft/resnet-101