search

Reagan1311 / ASGNet

Adaptive Prototype Learning and Allocation for Few-Shot Segmentation (CVPR 2021)
https://reagan1311.github.io/asgnet/
117 stars 15 forks source link

View the result in the original image #2

Closed Nelebos closed 3 years ago

Nelebos commented 3 years ago

When I want to view the prediction results of the pictures in the test set, I found that the code I wrote to draw the output results on the original pictures always has bugs and ambiguities. Can I get the code that compares the results in the paper?

When I am performing image inference, the input is the image to be detected and a picture of the target class and its mask picture, then how can I use a picture to quickly detect different pictures, what I actually want to say is: how It is better to detect unknown pictures, not that I can only use one picture for verification.

Hope to provide an idea

Reagan1311 commented 3 years ago

Hi, the visualization is achieved by adding the transparent segmentation output over the image. You can visualize the result with matplotlib package: plt.imshow(image) plt.imshow(mask, alpha=0.3)

I am a bit confused about your second question. Do you want to use the same support image and test different query samples? If so, you can fix the support feature, and feed the model with different query images.

Hope this helps.

Nelebos commented 3 years ago

thanks the reply,