Charlene Olive

I don't think it's an error per say, it's not very explicitly mentioned in the paper either, although during the experiments the authors did mention that they downsampled the images....

Hello, did you manage to solve this error? When I checked up, it was mentioned to upgrade typing extensions but I can't.

Nope I did not meet with any such error. What torch version are you using?

Regarding your code, what is the use of these lines? gg = np.zeros(gt_array.shape) gt_mask = np.where(gt_array > 0, 1, gg) determinant_array = gt_mask * input_array label_list = np.unique(gt_array) I saw...

Hello, for feature_maps.npy you can reimplement it from what is written in the paper. It says in the paper: To embed images such that the encoding represents such semantic information,...

> Hi, Thank you for your code. I am executing the code and I run into some troubles. Some files are missing like feature_maps.npy is missing. Kindly guide about it....

Hi, I find your model works well...although there seems to be a bit of bug with the utils/train.py file (I don't know for sure because I haven't looked detailedly at...

It seems that your Multi-head cross attention has some slight implementation differences from the paper. You did not rescale the resulting weight values with a sigmoid activation function. Is there...

Oh hmm, did you try on the Carvana dataset? I saw that you had the the script to preprocess the Carvana dataset. The code you currently have works well for...

I followed your current script and also used a batch size of 1. By the way, the sigmoid activation function is not the only implementation difference, but I am curious...