Did the official demo use better model than vit_h model?

[zxj7b80]

When I provide multiply points for the model sam_vit_h_4b8939.pth, bad result occurs. It's different from the official demo 'https://segment-anything.com/demo'. In official demo, better segment result occurs with more points prompt. So I wonder whether the official demo used better model than sam_vit_h_4b8939.pth.

[githublqs]

I also have this question https://github.com/facebookresearch/segment-anything/issues/346

[AlexLee1235]

In my case, when I prompt it iteratively (add one point a time and use old mask as prompt), it's result is more like the web demo.

for i in range(1,len(samPoints)): masks, scores, logits = predictor.predict( point_coords = np.array(samPoints[0:i]), point_labels = np.array(pointFlag[0:i]), mask_input = prev[None, :, :] if i > 1 else None, multimask_output = False, ) prev = logits[np.argmax(scores), :, :]

[sunsunnyshine]

I'm confused too!! The later is the demo result.

[sunsunnyshine]

I use the iterative prompt,and got this. The result has improved slightly, but it still doesn't meet the requirements compared to the demo. It seems like less point bright better results??

[sunsunnyshine]

In my case, when I prompt it iteratively (add one point a time and use old mask as prompt), it's result is more like the web demo.

for i in range(1,len(samPoints)): masks, scores, logits = predictor.predict( point_coords = np.array(samPoints[0:i]), point_labels = np.array(pointFlag[0:i]), mask_input = prev[None, :, :] if i > 1 else None, multimask_output = False, ) prev = logits[np.argmax(scores), :, :]

Hello, may I ask how the result looks after this processing? If you could provide a visual representation, I would greatly appreciate it!

[JI4JUN]

following

[315386775]

following