RuntimeError: inconsistent tensor size

[fasogbon]

Please, do you have any idea why I can run into problem of RuntimeError: inconsistent tensor size, expected tensor [100 x 3 x 128 x 128] and src [100 x 3 x 112 x 128] to have the same number of elements, but got 4915200 and 4300800 elements. I am new to this field. See below :

Reloaded modules: colmap_helpers, generate_volume_test, model <ipykernel.iostream.OutStream object at 0x0000024E05AE5438> Loading the trained model... <ipykernel.iostream.OutStream object at 0x0000024E05AE5438> Successfully loaded the trained model. <ipykernel.iostream.OutStream object at 0x0000024E05AE5438> Loading the sparse model... <ipykernel.iostream.OutStream object at 0x0000024E05AE5438> Successfully loaded the sparse model. <ipykernel.iostream.OutStream object at 0x0000024E05AE5438> Creating VGG model... <ipykernel.iostream.OutStream object at 0x0000024E05AE5438> Successfully created VGG model. <ipykernel.iostream.OutStream object at 0x0000024E05AE5438> Start working on image 0/3. <ipykernel.iostream.OutStream object at 0x0000024E05AE5438> Working on patch at row = 0/3 col = 0/4 <ipykernel.iostream.OutStream object at 0x0000024E05AE5438> Working on patch at row = 0/3 col = 1/4 <ipykernel.iostream.OutStream object at 0x0000024E05AE5438> Working on patch at row = 0/3 col = 2/4 <ipykernel.iostream.OutStream object at 0x0000024E05AE5438> Working on patch at row = 0/3 col = 3/4 <ipykernel.iostream.OutStream object at 0x0000024E05AE5438> Working on patch at row = 1/3 col = 0/4 <ipykernel.iostream.OutStream object at 0x0000024E05AE5438> Working on patch at row = 1/3 col = 1/4 <ipykernel.iostream.OutStream object at 0x0000024E05AE5438> Working on patch at row = 1/3 col = 2/4 <ipykernel.iostream.OutStream object at 0x0000024E05AE5438> Working on patch at row = 1/3 col = 3/4 <ipykernel.iostream.OutStream object at 0x0000024E05AE5438> Working on patch at row = 2/3 col = 0/4 Traceback (most recent call last):

File "", line 1, in runfile('C:/Users/.../Desktop/DeepMVS-master/python/test.py', wdir='C:/Users/..../Desktop/DeepMVS-master/python')

File "C:\Users....\deepMVS2\lib\site-packages\spyder_kernels\customize\spydercustomize.py", line 668, in runfile execfile(filename, namespace)

File "C:\Users....\deepMVS2\lib\site-packages\spyder_kernels\customize\spydercustomize.py", line 108, in execfile exec(compile(f.read(), filename, 'exec'), namespace)

File "C:/Users/..../Desktop/DeepMVS-master/python/test.py", line 253, in data_in_tensor[0, 0, :, 0, ...] = ref_img_tensor.expand(num_depths, -1, -1, -1)

RuntimeError: inconsistent tensor size, expected tensor [100 x 3 x 128 x 128] and src [100 x 3 x 112 x 128] to have the same number of elements, but got 4915200 and 4300800 elements respectively at c:\anaconda2\conda-bld\pytorch_1519492996300\work\torch\lib\th\generic/THTensorCopy.c:86

[fasogbon]

Or can you please provide a test examples (with the txt file exports from colmap) thanks

[phuang17]

Can you print out image_width and image_height in test.py? Do they match the actual image size?

[fasogbon]

See the attached images, i dont see any issue with the image_width and image_height

[phuang17]

That's strange.... Can you also print out start_x, start_y, next_start_x, and next_start_y?

[fasogbon]

Yes its strange! see theattached screenshot

[fasogbon]

• current start_y should be next_start_y from previous loop which is 128 but for weird reason its taking it as 112

[fasogbon]

Thank you for your feedback. My problem is eventually solved.

• It was due to conversion issue between python 2.7 and 3.5
• mismatch of int and float
• use of round vs int(container)

[phuang17]

Glad that you resolved it! And yes, my codes are for Python 2.7. Sorry about this limitation.