Anyman552
Anyman552
The code works. I got similar errors because of incompatible versions of tensorflow, cuda, cudnn, keras. It works for me with Cuda 10, cudnn 7.6, tensorflow-gpu==1.15.3 and Keras==2.2.4.
Unfortunately no. I only use train.py. Sorry!
How do you convert from darknet-format to the format of keras-yolo3 (x_min,y_min,x_max,y_max,class_id) ? Have you checked if this conversion doesn't mess up anything? In the beginning I had similar problems...
The coordinates are looking good. Do you provide the right path to the annotation_path (https://github.com/qqwweee/keras-yolo3/blob/e6598d13c703029b2686bc2eb8d5c09badf42992/train.py#L17) ? Have you edited yolov3.cfg to your needs? Look at : https://github.com/AlexeyAB/darknet#how-to-train-to-detect-your-custom-objects However, the code...
This should be fixed! Normally vue takes care of this: https://vuejs.org/v2/guide/security.html#HTML-content.
I'm not sure if passing the config as first option is the solutution. I'll take a look on it and submit a PR.
I've submitted a PR: #94
I agree, this is a well-known floating-point issue in JavaScript. We are using this library to provide a preview of Camunda calculations in our backend. Unfortunately, the discrepancies in calculation...