Neural network -- Python implements BP neural network algorithm (Theory + example + program)

1, Multilayer perceptron model based on BP algorithm The multilayer perceptron using BP algorithm is the most widely used neural network so far. In the application of multilayer perceptron, the single hidden layer network shown in Figure 3-15 is the most common. In general, it is customary to call a single hidden layer feedforward network a th ...

Posted by Eratimus on Tue, 30 Nov 2021 21:35:36 -0800

[TextCNN full version] fast + high accuracy baseline

preface: Two months ago, I wrote the complete steps of TextCNN (less than 60 lines of code), but did not take into account the subsequent engineering deployment and large amount of data (unable to load all into memory), so today I made a transformation and optimization according to the actual case. The operation steps of TextCNN can generally b ...

Posted by FuriousIrishman on Tue, 30 Nov 2021 19:18:57 -0800

PPASR streaming and non streaming speech recognition

PPASR streaming and non streaming speech recognition The project will be divided into three stages: beginner ,Progressive class and Final stage Branch, which is currently the final level and continuously maintains the version. PPASR Chinese name PaddlePaddle Chinese speech recognition (PaddlePaddle Automatic Speech Recognition), is a PaddlePa ...

Posted by vitch2002 on Tue, 30 Nov 2021 08:54:09 -0800

[model training] ubuntu compiles Darknet and YOLO training

Welcome to my official account, reply to 001 Google programming specification.  O_o   >_<   o_O   O_o   ~_~   o_O   Hello, I'm Jizhi horizon. This paper introduces the method of compiling darknet and yolo training on ubuntu.1. Compiling darknet1.1 compiling opencv     I won't say much about the installation of cuda and ...

Posted by surajkandukuri on Tue, 30 Nov 2021 05:17:38 -0800

[model training] ubuntu compiles Darknet and YOLO training

Welcome to my official account, reply to 001 Google programming specification.   O_o   >_<   o_O   O_o   ~_~   o_O   Hello, I'm Jizhi horizon. This paper introduces the method of compiling darknet and yolo training on ubuntu. 1. Compiling darknet 1.1 compiling opencv   I won't say much about the installation of cuda and ...

Posted by AZDoc on Tue, 30 Nov 2021 03:30:32 -0800

python magic function

preface This blog mainly introduces Python's magic functions. In depth learning or python programming, python class writing will be more or less involved, including Python magic functions. For example, when writing a data loading generator, it may be involved__ next__,__ iter__ Function. Of course, the generator may be done with the keywo ...

Posted by lizard on Mon, 29 Nov 2021 20:15:32 -0800

Final: Reading the structure of the t5 model

From previous reading of the code, the key to discovering the problem is past_ Key_ A change in the value parameter makes the input less complex. The overall structure of the model (from outside to inside) The overall structure of the model determines the direction in which the data will operate. Frame structure diagram of the overall mod ...

Posted by gkostenarov on Mon, 29 Nov 2021 13:39:55 -0800

Automatic driving based on Unity

1. Process Software download and installationdata acquisitionCustom datasetModel buildingmodel trainingtestsummaryfollow-up Download address of this project GitHub 1. Software download and installation 1.Download address: https://github.com/udacity/self-driving-car-sim 2. After entering the link, you can choose your own platform to download ...

Posted by Plex on Mon, 29 Nov 2021 07:47:16 -0800

Interpretation of PixPro self-monitoring paper

PixPro is the first to use pixel level contrast learning for feature representation learningThe above figure is the flow chart of the whole algorithm, which will be analyzed in detail nextForward propagationInput is the input image, and the dimension size is (b, c, h, w)augmentation: cut the same input in random size and position and reduce it ...

Posted by Darhazer on Mon, 29 Nov 2021 00:44:25 -0800

log usage

log usage It is inevitable that we encounter bugs in the development process. How can we easily find bugs? There is a logging module in Python that can record what is wrong and record relevant information to help us debug easily log level Logs are divided into five levels, from low to high: 1. DEBUG 2. INFO 3. WARNING 4. ERROR 5. C ...

Posted by svivian on Sat, 27 Nov 2021 20:01:35 -0800