Inicio Explorar Axuda
Iniciar sesión
yct
/
LearnTF
1
0
Fork 0
Ficheiros Incidencias 0 Pull Requests 0 Wiki

Sen descrición

Rama: master
Ramas Etiquetas
LearnTF
ZIP TAR.GZ
youchen 56ebfc2536 keras usage and other hight level apis %!s(int64=5) %!d(string=hai) anos
.idea 1f26f95c7c add LeNet5 cnn structure, conv, polling, dropout. cnn must be trained in a better GPU %!s(int64=5) %!d(string=hai) anos
Encapsulation 56ebfc2536 keras usage and other hight level apis %!s(int64=5) %!d(string=hai) anos
LeNet5 56ebfc2536 keras usage and other hight level apis %!s(int64=5) %!d(string=hai) anos
MNIST_data 20c7ffabb3 squeeze file structure %!s(int64=6) %!d(string=hai) anos
RNN b73da0e7c4 tensorboard usage. RNN structure %!s(int64=5) %!d(string=hai) anos
TF_Init 4f40fbb383 some notes for the TF installation %!s(int64=6) %!d(string=hai) anos
img_proc b73da0e7c4 tensorboard usage. RNN structure %!s(int64=5) %!d(string=hai) anos
inceptionv3 acbb23da1d inceptionv3 nn structure, img_proccess, tfrecord read & write, multiThread, coordinator and queueRunner %!s(int64=5) %!d(string=hai) anos
mnist_number_recognition 1f26f95c7c add LeNet5 cnn structure, conv, polling, dropout. cnn must be trained in a better GPU %!s(int64=5) %!d(string=hai) anos
mnist_restructured 1f26f95c7c add LeNet5 cnn structure, conv, polling, dropout. cnn must be trained in a better GPU %!s(int64=5) %!d(string=hai) anos
tests 30ef1bf358 restructured nn for mnist number recognition, together with saved nn weights, diagrams and photos %!s(int64=6) %!d(string=hai) anos
.gitignore 448ad3851d implement LeNet5 structure using dataset read from tfrecord. code debug. image sometimes stored as uint8 or float32, which need to be clear in mind when using the dataset. Some image preprocessing functions may require 3 channels image rather than grayscale image, such as modify saturation, hue and contrast. %!s(int64=5) %!d(string=hai) anos
LICENSE 591b2bde87 Initial commit %!s(int64=6) %!d(string=hai) anos
README.md 591b2bde87 Initial commit %!s(int64=6) %!d(string=hai) anos
__init__.py 448ad3851d implement LeNet5 structure using dataset read from tfrecord. code debug. image sometimes stored as uint8 or float32, which need to be clear in mind when using the dataset. Some image preprocessing functions may require 3 channels image rather than grayscale image, such as modify saturation, hue and contrast. %!s(int64=5) %!d(string=hai) anos

README.md

TF

repo for TF learning