Ei kuvausta

14 Commitit

1 Haarat

0 Julkaisut

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

TF

repo for TF learning