vishal2188 / therisurnet---a-computationally-efficient-thermal-image-super-resolution-network Goto Github PK

FOA, thanks for your amazing work.
the dataset links of this project were failed, Could you update the links?
THANKS.

This is not an issue, but a question, which I am unsure whether it is relevant to be asked here, but I wonder if you would answer me.

In the PBVS2020 paper, evaluation 2, where the Domo images set was super-resolved and compared with Axis images set: the model that was used for that evaluation, what was it trained on?

Because I am trying to do the evaluation 2 (which you do not report in your paper), and I am not sure whether you used the image pairs (HR-LR(bicubically downscaled)) to train that model, then you used it to super-resolve "real images".

Did my question make enough sense?

Thanks in advance.

Thank you so much for sharing

I am trying to retrain your network on the PBVS dataset, and I tried running your code without any modification, but I get this error:

Traceback (most recent call last):
File "main.py", line 185, in
main()
File "main.py", line 96, in main
L1_loss = tf.compat.v1.losses.absolute_difference(y, t)
File "C:\Users\moaaz\anaconda3\envs\TherISuRNet\lib\site-packages\tensorflow_core\python\ops\losses\losses_impl.py", line 253, in absolute_difference
predictions.get_shape().assert_is_compatible_with(labels.get_shape())
File "C:\Users\moaaz\anaconda3\envs\TherISuRNet\lib\site-packages\tensorflow_core\python\framework\tensor_shape.py", line 1115, in assert_is_compatible_with
raise ValueError("Shapes %s and %s are incompatible" % (self, other))
ValueError: Shapes (4, 192, 192, 3) and (4, 256, 256, 3) are incompatible

Trying to find what is the cause of the problem, I found that y and t in main.py Line#92 are of different sizes. Digging further into it, I found that in model.py Line#75, you use the img_size3, img_size3 , where in model.py Line#95 you use size=[h * 4, w * 4] , and that is why y and t are resulting in different sizes. Is that how it is supposed to be?

I wonder if you can help me with it.

Hello Vishal,

Can you tell me what changes I need to do in order to achieve a scale of 2 or 3 instead of 4?

Thanks in advance.

Could you please update the download link for the result of PBVS validation set

sorry
the dataset links of this project were failed, Could you update the links?

i wanna download vgg19.mat
plz

thank you