Metadata-Version: 2.1
Name: deepblocks
Version: 0.1.0
Summary: Useful PyTorch Layers
Home-page: https://github.com/blurry-mood/Deep-Learning-Blocks
Author: Ayoub Assis
Author-email: assis.ayoub@gmail.com
License: LICENSE
Keywords: pytorch cnn layers
Platform: UNKNOWN
Requires-Python: >=3.7
Description-Content-Type: text/markdown
Requires-Dist: numpy (>=1.19.0)
Requires-Dist: pandas (>=1.2.4)
Requires-Dist: matplotlib (>=3.4.2)
Requires-Dist: opencv-contrib-python (>=4.5.1.48)
Requires-Dist: opencv-python (>=4.3.0.36)
Requires-Dist: torch (>=1.7.1)
Requires-Dist: torchvision (>=0.8.2)
Requires-Dist: pytorch-lightning (>=1.2.0)
Requires-Dist: pytorch-lightning-bolts (>=0.3.2)

# Deep-Learning-Blocks
A library with customized PyTorch layers and model components.

## What's available for use:
### **Layers**:
* [InputAware Layer](docs/CNN%20Layers.md#input-aware-layer)
* [Funnel ReLU](docs/CNN%20Layers.md#funnel-relu-frelu)
* [Flip-Invariant Conv2d](docs/CNN%20Layers.md#flip-invariant-conv2d-layer)
* [Squeeze-Excitation Block](docs/CNN%20Layers.md#squeeze-excitation-block)  

### **Loss Functions**:
* [Inverse Sigmoid](docs/losses.md#inverse-sigmoid-loss)
* [Cosine](docs/losses#cosine-loss)

### **Training Strategies**:
* [GA Trainer](docs/trainer.md#genetic-algorithm-trainer-ga)


