2017-05-31 13:21:05 -0600 | received badge | ● Scholar (source) |
2017-05-31 07:48:36 -0600 | commented answer | How to store negative float values in Mat object? Ohh! Got it, Thanks a lot :) |
2017-05-31 07:40:32 -0600 | asked a question | How to store negative float values in Mat object? Why am I not able to do this? When I display the Mat object, it shows 255 in place of -1. I want to have all of my pixel values in the range of -1 to 1. How can I achieve that? |
2017-05-29 06:42:09 -0600 | commented answer | Unknown type "CudaLong" of torch class "torch.CudaLongTensor" in parseTorchType Thanks a lot @dkurtaev . It finally worked! :D |
2017-05-28 11:38:09 -0600 | commented answer | Unknown type "CudaLong" of torch class "torch.CudaLongTensor" in parseTorchType This is the link to my trained model http://s000.tinyupload.com/index.php?... This is the link to my modified model, from which Softmax layer has been deleted: http://s000.tinyupload.com/index.php?... |
2017-05-28 11:09:09 -0600 | commented answer | Unknown type "CudaLong" of torch class "torch.CudaLongTensor" in parseTorchType 256x256 pixels. You can un-comment https://gist.github.com/nitinkgp23/ff... , to make sure it is 256x256 pixels. |
2017-05-28 08:04:27 -0600 | commented answer | Unknown type "CudaLong" of torch class "torch.CudaLongTensor" in parseTorchType This is the link to the cpp file https://gist.github.com/nitinkgp23/ff... and this is the link to data.lua file, that reads data: https://gist.github.com/nitinkgp23/42... and this is run.lua, the main file that is to be run https://gist.github.com/nitinkgp23/07... After saving the model, there is another file modify.lua that reads the saved model, replaces the softmax layer with identity, and saves it back. Thanks a lot. |
2017-05-28 00:59:25 -0600 | received badge | ● Enthusiast |
2017-05-27 16:10:29 -0600 | commented answer | Unknown type "CudaLong" of torch class "torch.CudaLongTensor" in parseTorchType This is a link to my model.lua file https://gist.github.com/nitinkgp23/1a... It is a 2 class classification problem. I am inputting a 256x256 size image. How do I know whether I put the input blob with incorrect size? Please tell me if I need to provide any other info. I really have to get this done :( |
2017-05-27 01:59:29 -0600 | commented answer | Unknown type "CudaLong" of torch class "torch.CudaLongTensor" in parseTorchType Hey, sorry if I am becoming a pain, but I really need to make through this. Any help will be highly appreciated.
I did as described in the torch tutorial, but in |
2017-05-26 07:18:08 -0600 | commented answer | Unknown type "CudaLong" of torch class "torch.CudaLongTensor" in parseTorchType I am stuck with another issue. I was following the dnn tutorial for caffe, and I found a line |
2017-05-26 07:13:12 -0600 | received badge | ● Editor (source) |
2017-05-26 06:48:08 -0600 | asked a question | Error while making a forward pass using net.forward() I have the following lines of code : After executing the third line, I get the following error:
I found out the line where the code was breaking and I did the assertion in my main function: which passed successfully. What can be the reason for the code failing? Is the Please help. |
2017-05-26 03:22:54 -0600 | commented answer | Unknown type "CudaLong" of torch class "torch.CudaLongTensor" in parseTorchType It worked! Thanks a lot! :) |
2017-05-25 07:34:14 -0600 | commented answer | Unknown type "CudaLong" of torch class "torch.CudaLongTensor" in parseTorchType Yes, I know that openCV supports only evaluation. But, how do I save the model without the LogSoftMax function? After training the model from torch, I get a model.net file, which I want to import in openCV. So, how do I modify this binary file? |
2017-05-25 01:16:40 -0600 | commented answer | Unknown type "CudaLong" of torch class "torch.CudaLongTensor" in parseTorchType Thanks @dkurtaev, but I will be glad if you could help me out a bit more. I understand that LogSoftMax can be replaced by Identity, but that can be done only in the eval mode right? We will need to have the LogSoftMax function during training. So, how do I modify the layers on the basis of which mode the model is working in? If I simply remove the softmax function or replace it with identity, the model won't converge. |
2017-05-24 06:30:12 -0600 | commented answer | Unknown type "CudaLong" of torch class "torch.CudaLongTensor" in parseTorchType Hello, I did as told, and saved the model in CPU mode. But, that error went away, and a new one came
|
2017-05-17 11:20:17 -0600 | asked a question | Unknown type "CudaLong" of torch class "torch.CudaLongTensor" in parseTorchType I have a trained torch model that I am trying to import in OpenCV. Upon importing the model by
I get the following error:
Why do I get this error? Is it because of my trained model? What should I do so that my model is successfully imported? I am using the latest opencv and opencv_contrib module. |