request for README of pytorch-ssd-mmd-coral about visda-2018-public HOT 8 OPEN

The whole code is written in a very sloppy way. I recommend to use TorchCV directly, which is what this project is based on anyway. Plus at least the implementation of Self-Ensemble is wrong (not that it would work for this task). I did not check the implementations of the other baselines, as I don't have a good understanding of them.

from visda-2018-public.

As for the "Connection refused" error, install and run wisdom server in parallel, or comment lines that start it. Not sure about the latter, are you sure you downloaded our gt files and provided paths to them?

from visda-2018-public.

Yep, I just downloaded the gt files mentioned in this page and modified the corresponding path in the source code. I used the images extracted from train.tar as training data and visda18-detection-train.txt/visda18-detection-test.txt as gt boxes.

The latter problem was actually caused by dimension mismatch. Sometimes a boxes with only 1 dimension was passed to the function. I fixed this problem by modifying the code this way:

xmin = w - boxes[..., 2]
xmax = w - boxes[..., 0]

from visda-2018-public.

BTW, according to this page, I found the "Connection refued" error can be solved by setting num_worker=0 in when defining torch.utils.data.DataLoader.

from visda-2018-public.

Well, another issue appeared when processing this line:

from visda-2018-public.

@heinzermch yep, I suspected that self-assembling code was probably wrong logically, but I would appreciate if you could point me more specifically towards what exactly is wrong with this implementation. As for the quality of code in the repo, it is pretty much torchcv SSD example with data readers for this specific dataset and somewhat different run logic since you have to train supervisely on source, unsupervisely on target, and eval on different splits of both. Pull requests are welcome :)

from visda-2018-public.

@chrisliu54 hi, did you solve this error?

from visda-2018-public.

After I turned to use official repo of TorchCV, some weird errors has gone since then : ）

from visda-2018-public.