User Portlet User Portlet

Giulio Alessandrini
Discussions
Just a note, `ResizeLayer` has been updated to work on arbitrary rank ResizeLayer[{1, 2, 3, 4, 5}][RandomReal[1, {3, 2, 2, 2, 2, 2}]] // Dimensions (* {3, 1, 2, 3, 4, 5} *)
The best importer right now is from ONNX so I would start with a Tensorflow -> ONNX converter like this https://github.com/onnx/tensorflow-onnx There is also a small tutorial by Microsoft ...
There are no secret advantages, just a misunderstanding. Indeed I am not sorting by `Last` but by `First` (see my post). I thought you where asking a general question about the sorting algorithms.
The low level PNG importer `ImageReadPNG` is automatically caching the result. If you use the internal function directly you must clean it up yourself with ``` Image`ImportExportDump`DeleteCachePNG[] ``` This should hopefully solve the memory...
It might be a bug, I cannot reproduce it in my version. You should contact the support team using https://www.wolfram.com/support/contact/email/?topic=feedback
Hi Michael, you can explore the internals of the `DimensionReducerFunction` to check the preprocessor—ideally you should be able to do ``` Information[_DimensionReducerFunction, "FeatureExtractor"] ``` but we have not hook it up there yet....
Thanks for the wonderful post and for making me discover Townscaper!
Color conversion using external profiles is very slow. I would suggest to plot `fujiPearlProfile`, save it and then combine it with a separate plot for each image using `Show`.
Let me build on your suggestion by comparing Classify and NetTrain on this problem. I will first import the dataset as "RawData" to avoid the automatic conversion of stuff like "2" from string to integer (just to avoid dealing with mixed data...
I went spelunking for some useful utility, but I could not immediately find one so I put something together quickly. It's bound not to be perfect. The main idea is to take the `FeatureExtractorFunction` processor information and graph the feature...