Practical operation -- cloud deep learning workstation configuration guide

Reprint address: https://zhuanlan.zhihu.com/p/336429888 https://mp.weixin.qq.com/s?__biz=MzI5MDUyMDIxNA==&mid=2247527704&idx=1&sn=c1234acc04c8f011c1786135a520c336&chksm=ec1c80e1db6b09f751a32bd4160120a1ddfd099c414c1e05a9a564d0224a51e9eca4ebfdd640&mpshare=1&scene=23&srcid=1222RYsP3MA07RymDXXlUioT&sharer_sharetime= ...

Posted by twister47 on Sat, 30 Apr 2022 20:52:28 +0300

Train of MMdetection Detailed explanation of Py source code

catalogue 1, Tools / train py 2, Detailed source code 3, Detailed explanation of core functions (1) build_detector(mmdet/models/builder.py) (2) build_dataset(mmdet/datasets/builder) (3) train_detector(mmdet/apis/train.py) (4) set_random_seed: (5) get_root_logger: 1, Tools / train py Optional parameters: # =========== optional ...

Posted by voitek on Sat, 30 Apr 2022 15:49:21 +0300

Super detailed explanation of CTC theory and actual combat

CTC introduction For speech recognition, the input of training data is a piece of audio and the output is its transcribed text, but we don't know how to align letters and speech. This makes training speech recognition more complex than it seems. It is very difficult and error prone for people to mark this alignment, because the boundaries ...

Posted by Poofman on Sat, 30 Apr 2022 05:37:58 +0300

Real-time face recognition and object recognition based on nodejs on Raspberry Pi 4B using tfjs-node

start I had this idea a few years ago. I wanted to be an assistant that can recognize faces and objects, and can recognize commands through simple dialogues. Similar to the offline enhanced version of Xiao Ai, I can monitor my cabin by the way. However, I was too busy at the end of the year and didn’t have the time and energy to toss. I ...

Posted by ludjer on Fri, 29 Apr 2022 15:52:37 +0300

pytorch train.py and test.py code flow

First explain train.py, including the following steps 1. Configure the training set and test set train_data = torchvision.datasets.CIFAR10(root="./dataset", train=True, transform=torchvision.transforms.ToTensor(), download=True) test_data = torchvision.datasets.CIFAR10(root="./dataset", train=False, t ...

Posted by CodeEye on Fri, 29 Apr 2022 00:13:17 +0300

2020-12-27 Ng Enda-C5 Sequence Model-w1 Recurrent Sequence Model (after-school programming 1-Building your Recurrent Neural Network - Step by Step to build RNN)

Original link If you can't open it, you can also copy the link to https://nbviewer.jupyter.org to open it. Welcome to the first assignment for Sequence Models in Course 5. In this assignment, you will implement your first recurrent neural network in numpy. Recurrent Neural Networks (RNN s) are "memory" and are very effective in ...

Posted by dooper3 on Thu, 28 Apr 2022 17:48:21 +0300

Tensorflow - fast RCNN network (RPN training)

Tensorflow fast RCNN network (RPN training) (II) In Tensorflow - fast RCNN network (I) blog, I simply explained the principle of fast RCNN network. The following blogs will implement the code step by step~ Here, I still want to thank the two leaders for their selfless sharing, otherwise I may not know until now~ Reprint principle article l ...

Posted by cheerio on Thu, 28 Apr 2022 17:19:32 +0300

TensorFlow in simple terms

TensorFlow in simple terms 1, Overview 1. Comparison of common deep learning frameworks 2.TensorFlow introduction TF2. The 0 model uses the latest architecture diagram TensorFlow resource 3. Installation of tensorflow (version 2.0) 4.tf.keras introduction tf.keras and keras API tf.keras dataset 1,The d ...

Posted by nevvermind on Thu, 28 Apr 2022 04:45:35 +0300

20 lines of code: image classification and prediction can be easily done in Python under Serverless architecture

Author Jiang Yu preface Image classification is a hot topic in the field of artificial intelligence. Popular interpretation is an image processing method that distinguishes different types of targets according to the different characteristics reflected in the image information. It uses computer to quantitatively analyze the image, and clas ...

Posted by newbeee on Thu, 28 Apr 2022 00:00:39 +0300

Pattern Recognition and Neural Network Final Review Knowledge Arrangement

1. There is a set of gene chip data, the number of samples is 216, of which 90 are lung cancers, and the rest are normal people. The gene chip data dimension of each sample is 10500. Plan to use 2/3 of the data for training, and the rest for testing. 1) required to use GA The algorithm implementation chooses from 10 key genes related ...

Posted by maxmjessop on Wed, 27 Apr 2022 12:27:40 +0300