Vineeth S Subramanyam

Opencv Error when running make

2

When i run make, it returns a linking error. /usr/bin/ld: CMakeFiles/YOLOv5LibTorch.dir/src/YOLOv5LibTorch.cpp.o: in function `main': YOLOv5LibTorch.cpp:(.text.startup+0xed7): undefined reference to `cv::putText(cv::_InputOutputArray const&, std::string const&, cv::Point_, int, double, cv::Scalar_, int, int, bool)' /usr/bin/ld:...

Issue with rendering of point cloud

1

I am trying to train a model for depth estimation through forward rendering, and run into the issue as shown in the image below.  I get a grid of...

What would you do to obtain the standard mean and deviation for multiple classes?

1

How do you calculate the standard mean and deviation for bounding box sizes for multiple classes, or for training on your own dataset.

What changes are needed to be made to the code for training on multiple classes including pedestrian and truck?

Are the Calib files in the kitti dataset not used for transformation from 2D to 3D coordinates?

Issue with imports

1

While running the FCN-8.py file, I get the error from keras.utils.np_utils import conv_input_length which is imported in the deconv file. I have installed np.utils separately but it doesnt seem to...

Modifying code for multi class

1

Would changing the number of classes in the model compile from 1 automatically retrieve the labels for the other classes, or the code for label preparation would also need changing?

How do you train the model for multiple classes. Also how do you calculate the standard deviation and mean for bounding box sizes for multiple classes or for a custom...