dropblock
by miguelvr
Implementation of DropBlock: A regularization method for convolutional networks in PyTorch.
AI summary
Convolutional regularizer
Regularizes convolutional networks by randomly dropping units in contiguous regions of feature maps
- stars
- 589
- forks
- 95
- watching
- 9
Similar projects
Found by comparing what the projects do, not just their names.
Noisy Dropout Regularization
This project explores training deep neural networks using noisy labels with dropout regularization to improve robustness.
Dilated RNNs
Implementations of Dilated Recurrent Neural Networks in PyTorch
Deblurring model
A PyTorch implementation of an attention network for dynamic scene deblurring
Feature map refiner
PyTorch implementation of the CBAM module for refining feature maps in deep networks
Batch normalization alternative
An implementation of Filter Response Normalization Layer in PyTorch to improve the training of deep neural networks by eliminating batch dependence.
Neural network architecture
An implementation of a 1-bit weight neural network architecture using PyTorch
Label regularization
An implementation of a regularization technique to improve the accuracy of deep learning models trained with noisy labels.
Image deblurring software
Implementation of an algorithm for single image deblurring in images with defocus blur
Downsampling library
A PyTorch implementation of compact bilinear pooling, an efficient downsampling technique used in computer vision and other image processing applications.
Deformable Convolver
An implementation of Deformable Convolution in PyTorch using CUDA.
Pruning tool
This project provides a PyTorch implementation of pruning techniques to reduce the computational resources required for neural network inference.
CNN builder
A Python implementation of a Convolutional Neural Network from scratch using NumPy for building CNNs from scratch
Image classifier
Implementing a deep learning framework for image classification using Residual Attention Network architecture
CNN model
An implementation of a lightweight convolutional neural network architecture for mobile devices
Deblurring model
Develops a deep learning model for single image deblurring with improved performance and computational efficiency
