RoIAlign.pytorch

RoIAlign.pytorch copied to clipboard

TypeError from crop_and_resize.py : "initializer for ctype 'struct THCudaTensor *' must be a pointer to same type, not cdata 'struct THFloatTensor *"

2

Hi, I am trying to use the CropAndResize function on a GPU and am getting the following error. Does anyone have any suggestions? I am running with Python 3.7 and...

kathydo

My computer has no GPU or cuda, so can I use this code?If yes, how do I use it?Need win10 compile again?!Can it be compiled in Ubuntu16.04 and used directly...

YuanGao-cs

Thanks for this package. Is it possible to add `nms` too in this package? that way we have all we need for mask rcnn in one package :)

IssamLaradji

I've run some tests in order to try and understand how exactly this implementation works. Let's suppose my features are as follows: ``` input: tensor([[[[0., 1., 2., 3., 4., 5.,...

lozino

why can not use float64

1

I have debugged the code for about ten years. Finally, I found cannot use dtype of the box as float64. WHY?????????????????????????????????????????????? I think this code is a little bit stupid.

wu-zhonghua

crop a patch from image

2

I write a simple test code `code 1` as follows. I first generate a 3D ndarray randomly, and add a new dimensionality to represente the batch_size dimension. The box is...

liuqk3

It supports batchsize>1？

1

Hi, dose it support batchsize>1?

gjd2017

Hi, thanks for your sharing codes. So how about the GPU memory cost compared with original RoiPool? And it seems like the function grid_sample in PyTorch could also do the...

sshaoshuai

error with test.py

2

Hi, When i run test.py, there is an error occured, as follows: F tensorflow/stream_executor/cuda/cuda_driver.cc:334] current context was not created by the StreamExecutor cuda_driver API: 0x3af31a0; a CUDA runtime call was...

xpain1