Model-J ResNet
Collection
1001 items • Updated
Model-J: ResNet Model (model_idx_0864)
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 | 0.0001 |
| LR Scheduler | cosine |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 864 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9720 |
| Val Accuracy | 0.8805 |
| Test Accuracy | 0.8818 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
skunk, cattle, raccoon, lion, shrew, sunflower, possum, house, butterfly, boy, pear, palm_tree, baby, poppy, chimpanzee, bee, hamster, aquarium_fish, spider, man, shark, pickup_truck, can, train, bus, fox, dinosaur, cloud, lobster, turtle, bear, plate, chair, maple_tree, camel, clock, flatfish, whale, tiger, oak_tree, couch, forest, worm, beetle, willow_tree, cockroach, table, sea, orange, wolf
- Downloads last month
- 1
Model tree for ProbeX/Model-J__ResNet__model_idx_0864
Base model
microsoft/resnet-101