HuguesDug

I over simplified my example to make it clear. And your last answer is exactly what I inted to do : get a layer that copy a arbitrary region of...

Would work... but I am going to have something like 200 inputs... I think getting a strip along x or along y would be better. A layer type : TNnetLayercopy(inputx,inputy,...

Hello, After reviewing the WEB, the solution to the problem would be something like this. It is the way "Keras/Tensorflow" operates. # define two sets of inputs inputA = Input(shape=(32,))...

Excellent ! However, I am lost with your example I guess it should be as follow, as voutput does not have same number of cnt as inputs ? for EpochCnt...

OK with the example. I will test on my dataset and will report if I see a bug or a problem. But it sounds all good.

Hello, I tried to compile the new release with Delphi 10.3.3, release mode. 3 errors are raised : - neuralnetwork.pas, procedure TNNet.Compute(pInput: array of TNeuralFloatDynArr); **line 8063 :** Compute(pInput[0]); Error...

Hello, Yes, your remark is correct : directly removing from database without going throught the API. Though, Android App or Web version do a resync of the cache when you...

I fear the TTL will not suite my need. I want to delete only read messages after a period, unread can stay on the server for unlimited period of time....

Hello, Would be great to have the option that user can opt for deleting only read messages that have reached the TTL, not all the messages.

Checking log in depth, it seams it is an older bug than a recent one... it just happen more often now.