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