Last week, I followed a latest CVPR paper: Track to Detect and Segment: An Online Multi-Object Tracker. I followed this work, and realized it. This work concentrates tracking, detecting, segmenting together, and can also detect a 3D model of objects. Besides, all the work can fluency run on videos.
I basically finished learning the pytorch lesson and tensorflow2 lessons. And I start to build some easy training model demos. I tried to build a classifier of RMB. And did some experiments.
I continued to learn the tensorflow2.0 and keras through online video lessons. I have learned the whole progress of the deep learning, including the pre-processing of dataset and the construction of deep learning modules. Though I am not very good at it now, but I will try to acquire all these skills soon.
I have finished the GUI Design of image processing and git push it to the gitlab. The GUI now can transform the image to grayscale, rotation, and inverse.
I am make a latex version of my AROB thesis, but I still not finish it.
This week, I cost 3 days to reviewed all the details of PYTHON3.
And then I cost 2 days to learn the general use of docker, through a set of teaching video. I now understand how to start a project in a docker container, and how to make … Continue Reading ››