search

DeepTrial / Retina-VesselNet

A Simple U-net model for Retinal Blood Vessel Segmentation based on tensorflow2
305 stars 76 forks source link

Test err #26

Closed llmir closed 5 years ago

llmir commented 5 years ago

Traceback (most recent call last): File "main_test.py", line 40, in main_test() File "main_test.py", line 34, in main_test drawCurve(gtlist,[problist],modelName,'DRIVE',config.checkpoint) File "/home/mir/project/Retina-VesselNet/perception/metric/segmention_metric.py", line 209, in drawCurve (FPR, TPR, AUC), (Precision, Recall, MAP),IoU = process.statistics() File "/home/mir/project/Retina-VesselNet/perception/metric/segmention_metric.py", line 38, in statistics assert(len(self.groundtruth)==len(self.probgraph)) AssertionError

could anyone tell me why would this happen and how to solve it? thx a lot!

DeepTrial commented 5 years ago

@llmir maybe you can check whether the num of gt images is right?

llmir commented 5 years ago

20 orgins and 20 gts, i haven't make any changes yet o(╥﹏╥)o. btw，would you mind telling me your wechat☺

llmir commented 5 years ago

[Info] Analyze filename... 05_test new full images shape: (1, 588, 568, 1) 11445/11445 [==============================] - 6s 549us/step N_patches_h: 109 N_patches_w: 105 N_patches_img: 11445

According to the dimension inserted, there are 1 full images (of 588x568 each) 11445 11445 using avg (584, 565, 1) [INFO] Metric results... 0%| | 0/255 [00:00<?, ?it/s]

why 584 565? is this the reason?

DeepTrial commented 5 years ago

wechat id：angularlock. Maybe that is the problem, i have not checked the code

llmir commented 5 years ago

all you have to do is delete the origin imgs in results, and this err solved.