tensorflow2.3 realize PPLCNet -- a lightweight backbone network with faster speed and higher accuracy

1. Preface PPLCNet is a lightweight and high-performance network PP lcnet designed by Baidu team in combination with the end-to-side reasoning characteristics of Intel CPU. The proposed scheme achieves better delay accuracy balance than ShuffleNetV2, MobileNetV2, MobileNetV3 and GhostNet in image classification tasks. This paper proposes a li ...

Posted by lakilevi on Wed, 06 Apr 2022 07:36:56 +0300

China Mobile integration - resumption of the first OneCity Programming Competition

China Mobile integration - resumption of the first OneCity Programming Competition Official account: ChallengeHub Competition link: https://js.dclab.run/v2/cmptDetail.html?id=457 Code link of this article: https://github.com/yanqiangmiffy/One-City-Challenge/tree/master/code 1. Competition background The theme of this OneCity programming co ...

Posted by Arsench on Tue, 05 Apr 2022 22:18:36 +0300

Transfer learning demonstration of computer vision

This paper describes how to use transfer learning to train a convolutional neural network for image classification task. For more on migration learning, see cs231n notes. About these notes: In fact, people usually don't train a whole convolutional neural network from scratch (starting with the random initialization weight), because there is u ...

Posted by happypete on Mon, 04 Apr 2022 09:06:07 +0300

Machine learning notes - use CNN and LSTM to generate text descriptions for images

1, Task description Seeing an image, your brain can easily distinguish what the image is about, but can the computer distinguish the content represented by the image? With the progress of deep learning technology, the availability of large data sets and computer capabilities, we can build models that can generate descriptions for images. The ...

Posted by kayess2004 on Mon, 04 Apr 2022 04:30:36 +0300

Detailed explanation of YOLO v3 source code

0. Summary Recently, I studied yolo3, read many blogs and understood some theoretical knowledge, but it was still a little hard to learn. After reading the source code, I had a further understanding. Here, I will not repeat the network code. The network code is easy to understand. The following will give a detailed explanation and analysis of t ...

Posted by samdennis on Mon, 04 Apr 2022 01:07:15 +0300

Cuda 11.1 + 30 series graphics card + Python 1.8.0 + install flownet2 for Ubuntu 18.04 0

The 30 series graphics card does not support the lower version of cuda, so you can only use the new version of pytorch and compile flownet2 0, the package of three custom layers reported various errors due to version reasons. Try to run the compilation command of the old version when the compilation was successful, but the installation was s ...

Posted by temujinleal on Sun, 03 Apr 2022 12:14:00 +0300

Learning machine learning - practice training model (image segmentation, cell image)

Image segmentation - cell image Based on Pytorch, UNET model Model learning comes from: (thank you for such a detailed article) https://github.com/Jack-Cherish/Deep-Learning Other websites: (1) pytorch novice tutorial https://pytorch.org/tutorials/beginner/deep_learning_60min_blitz.html (2) UNET paper https://arxiv.org/pdf/1505.04597.pdf (becau ...

Posted by globetrottingmike on Sun, 03 Apr 2022 03:15:30 +0300

Weekly report from March 28, 2022 to April 3, 2022

abstract The first part of the paper is spatio-temporal sequence meteorological prediction, which involves deep problems such as sphere manifold, geometric space mapping and so on. Based on some prior knowledge, it makes data mining and other analysis for environmental data. The second part studies the basic knowledge of GAN. Reading lite ...

Posted by yogadt on Sat, 02 Apr 2022 18:44:19 +0300

Practical cases of in-depth learning: two categories of film reviews

The first practical case of in-depth learning: classification of film reviews Official account: machine learning grocery storeAuthor: PeterEditor: Peter Hello, I'm Peter~ This is Machine Learning Grocery~ The case of this paper explains an important problem in machine learning: classification. This paper is a practical case in Python ...

Posted by Minase on Sat, 02 Apr 2022 18:13:36 +0300

[project practice] AUTOVC code analysis - model_vc.py [updating]

AUTOVC code analysis -- model_vc.py Introduction This project is a speech conversion project based on AUTOVC model, which is implemented by PyTorch( Project address).         AUTOVC follows the framework of automatic encoder and only trains the loss of automatic encoder, but it introduces carefully adjusted dimensionality reduction and d ...

Posted by meow on Sat, 02 Apr 2022 01:24:25 +0300