Mohammed Al-Rawi

> Yes, you need to revert back to TF 1.x Unfortunately they broke many things with the new version Hopefully it will work, let me know! It would be nice...

Hi, since I could not find a workable dataloader in PyTorch, I finally managed to write one and mask-rcnn is up and running now. However, I found that some samples...

Well, sorry if I was not clear enough, I am speaking about the samples' annotations loaded via ` modanet2018_instances_train.json` that supposedly have annotations to all the 53K images. In the...

I gave the code a go, since I was iterating over `K=1,..., n`; seems that `K=1` was the source of the problem. Although there might not be sense of using...

Hi @mdbloice there was something that resulted in this type _E datatype when I used `image.convert('L') ` ! Not sure if it was my mistake? Apparently, my input image was...

Well @mdbloice, it is a bit confusing to go back to the original code, as I have done a lot of changes to the code, also I am using git...

Oh, I have just remembered that I was using this function to convert the image to binary `image = image.point(lambda p: int(p < some_threshold_value) )` and not `convert('L')` ``` def...

@wishforgood Maybe you need to reduce the training batch size (in the config file) from 128 to something small,like 32, if your GPU memory is much lower than the Titan...

> @svekars and @morawi I'd like to know if this is still an unresolved issue. If so, then I'd like to work on it 😊 **From what I remember:** I...

> @morawi Thanks for sharing your code. I have a same question and a suggestion if you could put a tutorial for how we can run the code. Sorry for...