 youchen
|
56ebfc2536
keras usage and other hight level apis
|
5 gadi atpakaļ |
|
youchen
|
b73da0e7c4
tensorboard usage. RNN structure
|
5 gadi atpakaļ |
|
youchen
|
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 gadi atpakaļ |
|
youchen
|
acbb23da1d
inceptionv3 nn structure, img_proccess, tfrecord read & write, multiThread, coordinator and queueRunner
|
5 gadi atpakaļ |
|
youchen
|
1f26f95c7c
add LeNet5 cnn structure, conv, polling, dropout. cnn must be trained in a better GPU
|
5 gadi atpakaļ |
|
youchen
|
20c7ffabb3
squeeze file structure
|
6 gadi atpakaļ |
|
carbo-T
|
30ef1bf358
restructured nn for mnist number recognition, together with saved nn weights, diagrams and photos
|
6 gadi atpakaļ |
|
carbo-T
|
cb4034113f
add previous python files
|
6 gadi atpakaļ |
|
carbo-T
|
b1cbb82d80
mnist dataset training and validation
|
6 gadi atpakaļ |
|
youchen
|
9d8052225d
tensorflow basic operations with a NN sample
|
6 gadi atpakaļ |
|
youchen
|
4270ed650e
the first step
|
6 gadi atpakaļ |
|
carbo-T
|
4f40fbb383
some notes for the TF installation
|
6 gadi atpakaļ |
|
carbo-T
|
75baf32fa7
record system information for the TF
|
6 gadi atpakaļ |
|
carbo-T
|
591b2bde87
Initial commit
|
6 gadi atpakaļ |
