These are chat archives for deeplearning4j/deeplearning4j
**PLEASE NOTE: 🚨**This is not an all-purpose hotline for deep learning, and we don't have the resources to support DL frameworks other than DL4J. So please focus questions on Deeplearning4j and ND4J. - Room Guidelines: https://github.com/deeplearning4j/deeplearning4j/blob/master/deeplearning4j/GITTER_GUIDELINES.md - Ask your question first instead of asking to ask or introducing yourself. - Please get started here: https://deeplearning4j.org/docs/latest/deeplearning4j-quickstart
@AlexDBlack Greetings, again, so I have made an ObjectRecordReader for my project. Everything seems to be in order. I construct my model with the output layer being a Yolo2OutputLayer as in the example HouseNumberDetection.java. However when I run my model I get the following error, which I do not see when running the example HouseNumberDetection.java
Exception in thread "main" org.nd4j.linalg.exception.ND4JIllegalStateException: Shape of target array for reduction [[1, 53, 1]] doesn't match expected [[1, 112, 6]]
Since I do not see this error in the example, I assumed it was my record reader, but I find not problems there.
Any insights for me?
What is a 2x downsample? 2x2 kernel with stride 2x2?
if you go for downsampling though, I think your only option would be 2x downsampling
@AlexDBlack So going with the fix of the pipeline I now get a different reshape error, that I think has to to with the Yolo Layer itself reshaping from
Input format: [minibatch, B*(5+C), H, W] -> Reshape to [minibatch, B, 5+C, H, * W
new error is
New shape length doesn't match original length:  vs . Original shape: [1, 25, 56, 3] New Shape: [1, 5, 19, 56, 3]
// i.e. [1, nan, 3, nan] INDArray a = ND4j.create(...) INDArray out = Nd4j.getExecutioner().execAndReturn(new MatchConditionTransform(d1, Conditions.isNan())); out = Transforms.not(out); // I want get only True by "out" index. so the result is [1, 3], and how to get it? [1, nan, 3, nan] out = [1, 0, 0, 1] result = [1, 3]