Welcome to CT-image-segmentation-of-pulmonary-embolism Discussions!

[FeijiangHan]

👋 Welcome!

We’re using Discussions as a place to connect with other members of our community. We hope that you:

• Ask questions you’re wondering about.
• Share ideas.
• Engage with other community members.
• Welcome others and are open-minded. Remember that this is a community we
  build together 💪.

To get started, comment below with an introduction of yourself and tell us about what you do with this community.

[Cuuuuu123]

Hello,when I use your code--UNet 2D to predict my test dataset, it always was error. So, I want to know how the form of the test dataset is and the images size should resize? Thank you.

[FeijiangHan]

Hi, the original dataset I used is the open-source pulmonary embolism detection dataset https://tianchi.aliyun.com/dataset/90713. I preprocessed it into 512x512 PNG images (for both data and labels).

[Cuuuuu123]

Oh, it's kind of you to reply my question. I do really want to know what the mean of this code in the generate_predict.py or generate_metric.py:
org_mask = cv2.imread(image.replace('image', 'label'), 0)
Dose it mean I need two files like my picture include images and masks? Or I have to take the images and masks in the same file instead of separating them. And I make sure that they have the same name and have resized the same size.
Thank you for your kindness reply me again.