pytorch version sample_code.py run error

[plutoyuxie]

pytorch version sample_code.py run error

[erezposner]

I will need more details. What image size are you using? did you set the dimensions properly?

[plutoyuxie]

Hi, thank you for the prompt response. I just use the sample script, nothing changed.
My pytorch version is 1.5, and cuda==10.1, win10

[plutoyuxie]

Hi, 'singlePatch' mode works well. This issue only occurs in 'allPatches' mode
Total time for C_I: 0.013318886756896972sec
Total time for C_P per Patch without warm up: 0.0009350776672363281sec
------- Comparison between a base_net single patch evaluation and slim_net -------
difference between the base_net & slim_net - 0.0000000000000

[erezposner]

please check the size of cropped_patches

[plutoyuxie]

slim_net_output_numpy.shape: (113, 960, 1280)
len(cropped_patches): 1228800
cropped_patches[0].shape: torch.Size([1, 1, 15, 15])
base_net_output_per_patch.shape: (113, 960, 1280)
cropped_batches.shape: torch.Size([10, 1, 15, 15])
y_base.shape: torch.Size([10, 113, 1, 1])
base_current_output.shape: (10, 113)
base_net_output_per_patch.shape: (113, 960, 1280)
index: 108153647
imH*imW: 1228800
base_net_output_per_patch.size: 138854400

[plutoyuxie]

It is solved by changing the line 177
ci, yi, xi = np.unravel_index(index, (slim_net.outChans, imH, imW))

[erezposner]

Changed these line. You can pull again
index = np.argmax(sum(abs(base_net_output_per_patch - slim_net_output_numpy)))
max_diff = np.max(sum(abs(base_net_output_per_patch - slim_net_output_numpy)))

[plutoyuxie]

Thanks a lot.

[plutoyuxie]

Hi, I have one more question.
If my own network consists of layers without striding or pooling, How do I transform Cp to Ci.
Does the function multiConv help?
@erezposner

[erezposner]

Please refer to the paper https://arxiv.org/pdf/1805.03096.pdf.
"In this paper,
we present an approach to compute patch-based local feature descriptors efficiently in
presence of pooling and striding layers for whole images at once"

This means that without pooling or stride layers there isn't any difference between Cp and Ci

[plutoyuxie]

I see, thanks.