Janpreet comments

Results 10 comments of


                                            Janpreet

What is prior_boxes_ssd300.pkl? Is there anyone knowing this?

@tachim , as you said for using priors we can use `model.predict(img)[0, :, -8:]` , that can be done without any prior training of network, right??

A comment has been added to the class

[email protected]

Multiprocessing for apriori algorithm doesn't work as expected

Hi @rasbt , I can take this up. There are several ways to implement multiprocessing I think. I was looking at the code and one possible place to use multiprocessing...

Multiprocessing for apriori algorithm doesn't work as expected

The generator as a list thing was exactly I was concerned about. Thanks a lot for pointing out `lazy_map` function. There is one more thing, as per my understanding, I...

Multiprocessing for apriori algorithm doesn't work as expected

I applied the discussed approach but somehow multiprocessing.Pool is running slower than the code running on single core code, any ideas on that?

Generating randomly distributed Gaussians for training

Hi all, thanks for the helpful discussion. @alessiapacca, would it be possible to give some hints on making files to build the executables for disflow, bilateralAdv, and gauss? I don't...

Generating randomly distributed Gaussians for training

Thanks for the reply @alessiapacca . So, the way I making their executables in Linux is by changing the .bat files to appropriate .sh files but I am facing some...

Generating randomly distributed Gaussians for training

Thanks @alessiapacca, that makes sense. I will try it and get back to you. Thanks again :)

Gradient Backpropagation through Tensorfield

Oh, Okay, thank you! It seems like cause there is no explicit dimension for batch, implementing it for a batch size of more than 1 would be difficult this way....

Different result form pytorch and tensorrt

I think this is due to no nms implementation as specified in Readme file