Claudio Michaelis

The project was built using Tensorflow 1 (I don't exactly remember which version) and Keras 2.1.6.

You will have to define the classes with a 1:1 correspondence in pascal and set them as active classes: ``` pascal_classes = [1,2,3,4,5,6,7,9,15,16,17,18,19,20,40,57,58,59,61,63] no_pascal_classes = [i for i in range(1,81)...

We did not evaluate performance on Pascal VOC. We did measure performance on COCO using the VOC classes as a split but in the end decided to go with the...

@NCTU-VRDL the learning rate decay step after 120 epochs is very important for performance. I'd guess this is the problem but let me know if the performance is still low...

What is the performance when you evaluate? Loss and AP are not always that correlated because the model uses a mixture of 5 loss functions. In my experience the classifier...

Is this detection or instance segmentation performance?

Can you test object detection? You are now the second person to report this and it seems as if something broke in the segmentation training. And can you visualize some...

A quick check did not turn up any obvious bugs in the model. I'll have to check some of the older commits to figure out, where the problem originated from....

I first want to check if training with an older commit of the repo works. In the end I did run the experiments which led to the pre-trained checkpoints at...

That's what I suspected. Won't be easy to fix as it is something that goes wrong during training and only for the mask branch (object detection and the pre-trained model...