search

hanna-xu / DDcGAN

Code of DDcGAN for infrared and visible image fusion and medical image fusion
154 stars 44 forks source link

Given MRI/PET data, how can we use your model to generate fusion results? #2

Open stevenffd opened 4 years ago

stevenffd commented 4 years ago

My MRI/PET images are all 256x256 pixels. Are there any relevant documents to help me? thank you~

hanna-xu commented 4 years ago

Put you test images in test_imgs and run main.py. This network has no limits on the resolution. 

---Original--- From: "stevenffd"<notifications@github.com> Date: Sat, May 9, 2020 09:20 AM To: "hanna-xu/DDcGAN"<DDcGAN@noreply.github.com>; Cc: "Subscribed"<subscribed@noreply.github.com>; Subject: [hanna-xu/DDcGAN] Given MRI/PET data, how can we use your model to generate fusion results? (#2)

My MRI/PET images are all 256x256 pixels. Are there any relevant documents to help me? thank you~

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub, or unsubscribe.

stevenffd commented 4 years ago

Thank you so much! Nice work.

stevenffd commented 4 years ago

Hi, I run your code in main.py. But I get the error "ValueError: Dimension 1 in both shapes must be equal, but are 256 and 64. Shapes are [1,256,256] and [1,64,64]. for 'concat' (op: 'ConcatV2') with input shapes: [1,256,256,1], [1,64,64,1], [] and with computed input tensors: input[2] = <3>". And I test in my own dataset (both images are 256 x 256 x 1, rgb image is converted I channel) and I get the error "ValueError: Shape must be rank 4 but is rank 5 for 'MirrorPad' (op: 'MirrorPad') with input shapes: [1,256,256,6,1], [4,2]". I am the new in tensorflow. Can you help me figure out?