Nessuna descrizione

14 Commit

1 Rami (Branch)

0 Rilasci

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

TF

repo for TF learning