deeplearning4j / deeplearning4j

Suite of tools for deploying and training deep learning models using the JVM. Highlights include model import for keras, tensorflow, and onnx/pytorch, a modular and tiny c++ library for running math code and a java based math library on top of the core c++ library. Also includes samediff: a pytorch/tensorflow like library for running deep learn...
http://deeplearning4j.konduit.ai
Apache License 2.0
13.67k stars 3.83k forks source link

docu improvement 'ETL images' #3851

Open coldwarrl opened 7 years ago

coldwarrl commented 7 years ago

The documentation, explaining the ETL process for images (https://deeplearning4j.org/simple-image-load-transforml) could be improved regarding describing the transformation possibilities:

"The pipeline can also be randomly shuffled with each transform in order to increase the available dataset. If you set shuffle to true, you can get an image pipeline that executes each transformation at random."

The randomization is not directly related to increasing the available dataset. At least me has confused this.

It would be also helpful to point to the related example: (https://github.com/deeplearning4j/dl4j-examples/blob/master/dl4j-examples/src/main/java/org/deeplearning4j/examples/convolution/AnimalsClassification.java)

tomthetrainer commented 7 years ago

Agreed,

A rough outline of an all inclusive doc on ETL for images would be best solution.

I think the classes/features that should be mentioned would be.

Path Label Generator shuffling transform pipelines including shuffling of transforms such as skew and crop scaling and standardizing

coldwarrl commented 7 years ago

dead link in https://deeplearning4j.org/model-zoo:

Transfer Learning

Pretrained models are perfect for transfer learning! You can read more about transfer learning using DL4J here.

tomthetrainer commented 7 years ago

Thanks, fixed the link.