Deepnet is an open-source library that can be used for solving problems of Computer vision in Deep Learning.
NOTE: This documentation applies to the MASTER version of DeepNet only.
Install the required packages
pip install -r requirements.txt
DeepNet currently supports the following features:
| Models | Description |
|---|---|
| ResNet | ResNet-18 |
| ResModNet | A modified version of ResNet-18 |
| CustomNet | A modified version of ResNet-18 |
| MaskNet3 | A model to predict the Segmentation mask of the given image. |
| DepthMaskNet8 | A model to predict the Monocular Depth Maps of the given image. |
| Functionality | Description |
|---|---|
| Train | Training and Validation of the model |
| Model | Handles all the function for training a model |
| Dataset | Contains classes to handle data for training the model |
- Mean Absolute Error
- Root Mean Squared Error
- Mean Absolute Relative Error
- Intersection Over Union Error
- Root Mean Square Error
| Loss | Description |
|---|---|
| Dice | ResNet-18 |
| SSIM | A modified version of ResNet-18 |
| MSE | Mean squared error (squared L2 norm) between each element in the input and target |
| BCE | Binary Cross Entropy between the target and the output |
| BCEWithLogitsLoss | Combination of Sigmoid layer and the BCE in one single class |
| RMSE | Root mean squared error (squared L2 norm) between each element in the input and target |
Weighted Combination of loss functions
- StepLR
- ReduceLROnPlateau
- OneCycleLR
- Resize
- Padding
- Random Crop
- Horizontal Flip
- Vertical Flip
- Gaussian Blur
- Random Rotation
- CutOut
| Utility | Description |
|---|---|
| GRADCAM | Calculates GradCAM(Gradient-weighted Class Activation Map) saliency map |
| GradCAMpp | Calculate GradCAM++ salinecy map using heatmap and image |
| LRFinder | Range test to calculate optimal Learning Rate |
| Checkpoint | Loading and saving checkpoints |
| ProgressBar | Display Progress bar |
| Tensorboard | Creates Tensorboard visualization |
| Summary | Display model summary |
| Plot | Plot the graph of a metric, prediction image and class accuracy |
DeepNet has the following third-party dependencies
- numpy
- torch
- torchvision
- torchsummary
- tqdm
- matplotlib
- albumentations
- opencv-python
For a demo on how to use these modules, refer to the notebooks present in the examples directory.
If you need any help or want to report a bug, raise an issue in the repo.