Žiadny popis

14 Commity

1 Vetvy

0 Vydania

youchen 56ebfc2536 keras usage and other hight level apis		5 rokov pred
.idea	1f26f95c7c add LeNet5 cnn structure, conv, polling, dropout. cnn must be trained in a better GPU	5 rokov pred
Encapsulation	56ebfc2536 keras usage and other hight level apis	5 rokov pred
LeNet5	56ebfc2536 keras usage and other hight level apis	5 rokov pred
MNIST_data	20c7ffabb3 squeeze file structure	6 rokov pred
RNN	b73da0e7c4 tensorboard usage. RNN structure	5 rokov pred
TF_Init	4f40fbb383 some notes for the TF installation	6 rokov pred
img_proc	b73da0e7c4 tensorboard usage. RNN structure	5 rokov pred
inceptionv3	acbb23da1d inceptionv3 nn structure, img_proccess, tfrecord read & write, multiThread, coordinator and queueRunner	5 rokov pred
mnist_number_recognition	1f26f95c7c add LeNet5 cnn structure, conv, polling, dropout. cnn must be trained in a better GPU	5 rokov pred
mnist_restructured	1f26f95c7c add LeNet5 cnn structure, conv, polling, dropout. cnn must be trained in a better GPU	5 rokov pred
tests	30ef1bf358 restructured nn for mnist number recognition, together with saved nn weights, diagrams and photos	6 rokov pred
.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.	5 rokov pred
LICENSE	591b2bde87 Initial commit	6 rokov pred
README.md	591b2bde87 Initial commit	6 rokov pred
__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.	5 rokov pred

TF

repo for TF learning