JXingZhao / EGNet

EGNet:Edge Guidance Network for Salient Object Detection (ICCV 2019)
311 stars 62 forks source link

Cannot save results on test images #23

Open fu123456 opened 4 years ago

fu123456 commented 4 years ago

Hi, I used a pre-trained model to test on my own images, and I add the following code:

elif sal_mode == 'f': # my specular highlight dataset
    self.image_root = '/home/user/sh/fg_SH_EGNet/SH_dataset/Test'
    self.image_source = '/home/user/sh/fg_SH_EGNet/SH_dataset/Test/test.lst'
    self.test_fold = '/home/user/sh/fg_SH_EGNet/output'

But in output/EGNetResNet50, there is no output images. I check the code, and find the save config code is

cv2.imwrite(os.path.join(self.config.test_fold,name_t, name[:-4] + '.png'), multi_fuse)

Please help me. Very thank you.

JXingZhao commented 4 years ago

Hi, You need to make a empty dir first.

From: GF notifications@github.com Date: 2020-02-04 13:38:58 To: JXingZhao/EGNet EGNet@noreply.github.com Cc: Subscribed subscribed@noreply.github.com Subject: [JXingZhao/EGNet] Cannot save results on test images (#23) Hi, I used a pre-trained model to test on my own images, and I add the following code: elif sal_mode == 'f': # my specular highlight dataset self.image_root = '/home/user/sh/fg_SH_EGNet/SH_dataset/Test' self.image_source = '/home/user/sh/fg_SH_EGNet/SH_dataset/Test/test.lst' self.test_fold = '/home/user/sh/fg_SH_EGNet/output' But in output/EGNetResNet50, there is no output images. I check the code, and find the save config code is cv2.imwrite(os.path.join(self.config.test_fold,name_t, name[:-4] + '.png'), multi_fuse) Please help me. Very thank you. — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub, or unsubscribe.

zhouzhouzheng commented 3 years ago

Hi, I used a pre-trained model to test on my own images, and I add the following code:

elif sal_mode == 'f': # my specular highlight dataset
    self.image_root = '/home/user/sh/fg_SH_EGNet/SH_dataset/Test'
    self.image_source = '/home/user/sh/fg_SH_EGNet/SH_dataset/Test/test.lst'
    self.test_fold = '/home/user/sh/fg_SH_EGNet/output'

But in output/EGNetResNet50, there is no output images. I check the code, and find the save config code is

cv2.imwrite(os.path.join(self.config.test_fold,name_t, name[:-4] + '.png'), multi_fuse)

Please help me. Very thank you.

您好,请问您是怎么解决的,我也遇到同样问题

cs19469 commented 2 years ago

Hi, I have the same problem, can you help me? Thanks.