Chaoxing Huang

icon indicating a website link https://huangchaoxing.github.io/

icon company The Chinese University of Hong Kong icon location Hong Kong SAR, China icon location PhD student at DIIR, CUHK, MRI, Deep Learning, Medical Physics

Results 7 comments of Chaoxing Huang

RuntimeError: invalid hash value

Did you guy solve this problem ?

what does num_frame_per_clib mean in train.py and test.py

@LossNAN I am also confused about the difference of 16 and 64. It seems for 3D CNN，if we train the model at 64 frames length then the test length should...

what does num_frame_per_clib mean in train.py and test.py

@HyunWoo-Nick I think the single test length should be 64 or 16, but you do multiple 64 or 16 to cover all the frames and do the average during testing....

Not all input data has been trained

All the training set should be trained in one epoch. Every-step is just a batch.

validation set and test set issue

Also, it seems that the data list used in rgb and optical flow training are all "flow_list"....we shall use rgb_list in rgb case.

How do you group the components with same frequency into one channel?

Here is my interpretation with an example. If you get an image of 224*224, and you would like to to divide them into 28 patches of a size of 8*8....

Why do you use inverse H?

Hi @giovannicaprio This is because we still crop from point P in the new image. We have warp P to a new destination point in the image using H and...