Нема описа

14 Комити

1 Гране

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

TF

repo for TF learning