resnet50_svhn / README.md
edadaltocg's picture
Upload README.md with huggingface_hub
1b9af58
|
raw
history blame
1.34 kB
---
language: en
license: mit
library_name: timm
tags:
- image-classification
- resnet50
- svhn
datasets: svhn
metrics:
- accuracy
model-index:
- name: resnet50_svhn
results:
- task:
type: image-classification
dataset:
name: SVHN
type: svhn
metrics:
- type: accuracy
value: 0.963160725261217
---
# Model Card for Model ID
This model is a small resnet50 trained on svhn.
- **Test Accuracy:** 0.963160725261217
- **License:** MIT
## How to Get Started with the Model
Use the code below to get started with the model.
```python
import detectors
import timm
model = timm.create_model("resnet50_svhn", pretrained=True)
```
## Training Data
Training data is svhn.
## Training Hyperparameters
- **config**: `scripts/train_configs/svhn.json`
- **model**: `resnet50_svhn`
- **dataset**: `svhn`
- **batch_size**: `128`
- **epochs**: `300`
- **validation_frequency**: `5`
- **seed**: `1`
- **criterion**: `CrossEntropyLoss`
- **criterion_kwargs**: `{}`
- **optimizer**: `SGD`
- **lr**: `0.01`
- **optimizer_kwargs**: `{'momentum': 0.9, 'weight_decay': 0.0005}`
- **scheduler**: `MultiStepLR`
- **scheduler_kwargs**: `{'gamma': 0.1, 'milestones': [75, 100, 150, 225]}`
- **debug**: `False`
## Testing Data
Testing data is svhn.
---
This model card was created by Eduardo Dadalto.