Jasper Brown
Jasper Brown
can you include the entire error trace
because it occurs at the end of your training epoch, it's likely to be a bug in your validation or test code. You can try setting the --steps argument to...
might be a tf version issue, are you using tensorflow 1.11? `pip install tensorflow-gpu==1.11`
see https://github.com/jaspereb/Retinanet-Tutorial/issues/7
Is the script actually finishing? Check the CPU usage spikes then drops off and the python script returns. It's not using your GPU so inference will take a bit longer,...
I believe it was TF 1.14 (definitely a TF v1 release) and keras 2.3 I need to update the tutorial to use a pip virtualenv image (or maybe docker) but...
Yes, you will need to annotate the object boundaries in the training set. The linked tutorial suggests using VGG Image annotator for labelling. LabelBox is also very good but more...
How you set up the file structure will depend on the dataset preprocessing script that you use (or write your own). The one for fasterRCNN will not work because it...
Sounds like the keras may have refactored this code in a version change. I think this describes the issue: https://stackoverflow.com/questions/62629864/typeerror-type-object-got-multiple-values-for-keyword-argument-training and the fix is to use keras version 2.3.1 instead...
It's probably also a versioning issue. Might be CUDA but there are some people reporting that eager execution issue for different tensorflow versions. https://github.com/tensorflow/tensorflow/issues/20372 Can you install tensorflow 1.11? Otherwise,...