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