Hojun Lee

https://github.com/dbolya/yolact/blob/57b8f2d95e62e2e649b382f516ab41f949b57239/eval.py#L159 You can export mask from here (It's already in numpy array). For example, you can do like the following: np.save('mask_data', masks.cpu().numpy())

numpy of mask has 3-dimension (instance, x, y). So, if you want to pull out 1st instance, for example: mask = np.load('./mask_data.npy') solutions = np.argwhere(mask[0] != 0) This will give...

I'm not exactly sure what you mean by "background truth". Are you talking about image input without any mask?

The npy file contains pixel locations of the object you detected in 640x480 image. Can't you just generate 640x480 black background and convert the pixels corresponding to the npy file...

@amaanda May I ask how many dataset you had and how long you trained to get this mAP? Did you change learning rate or max_iteration? I'm doing a similar stuff...

As far as I understand, FEATURES_XX is a dimension of latent space. You should change out_channels if you want to generate images with different sizes

I was able to install the package with GPU support in the Google colab. To do this, we first have to setup the runtime mode to "GPU" and run the...

I also have the same issue with my own Vercel. It's been like this the entire day and still not working. I even tried to redeploy the project but did...

> @lucidrains I have the same issue, and cannot get a single layer to run with 12GB GPU Memory. Maybe my understanding of the layer is incorrect but I have...