Няма описание

14 Ревизии

1 Клонове

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

TF

repo for TF learning