nicolasrosa

"SIFT" -> "ORB"

Is dropout disabled?

1

"Following the set of these up-sampling blocks, dropout is applied and succeeded by a final convolutional layer yielding the prediction." However, in the fcrn.py code, the value of keep_prop is...

How many trainable parameters?

1

Hello, in your article you inform that the encoder used has 51M trainable parameters. What about the total number of trainable parameters? Does this value include the "Dense feature extractor"...

[PR] Distributed Tutorial Series

3

Hello Pytorch, When trying to run the DDP scripts I made some minor updates on the provided code. I hope the proposed changes can benefit others. Best regards, Nícolas Rosa

Hello @gaoxiang12, According to the official documentation of OpenCV, the arguments of `cv2::triangulatePoints()` should be the projection matrices and the feature points coordinates, but I think it is not clear...

[Ch7, 7.7.3] Questions

2

Hello @gaoxiang12, Sometimes I get very confused about the notations used. For example, in topic 7.7.3, I believe that for being consistent with those presented in chapter 5, we can...

Hello @gaoxiang12, In the equations 2.1, you used the following expression for the Motion Model:  I believe it should be:  Am I right? I saw this formulation...

Chapter 7, 7.4 Practice: Different Results from book, pose_estimation_2d2d.cpp

1

Hello @gaoxiang12, I just finishing Practice 7.4, I noticed some slight differences between the results from the `slambook2/ch7/pose_estimation_2d2d.cpp` code and the results presented in the book. The first one, the...

[Bug]: Doesn't show 1-channel image by using matplotlib.image.AxesImage.set_data()

13

### Bug summary I could not plot a 1-channel image while I was trying to populate a Subplots figure, although I can visualize it by using plt.imshow(). ### Code for...