stuarteiffert/RNN-for-Human-Activity-Recognition-using-2D-Pose-Input

Data set input

666tua opened this issue · 3 comments

666tua commented

The data set I downloaded from MHAD's official website is in.mat format. How to convert to txt file.What is the format of the txt file you entered?

stuarteiffert commented

It doesnt need to be in any specific file format as long as the output of load_x and load_y is a 2D array of kpts per frame, eg

[[j0_x, j0_y, j1_x, j1_y , j2_x, j2_y, j3_x, j3_y, j4_x, j4_y, j5_x, j5_y, j6_x, j6_y, j7_x, j7_y, j8_x, j8_y, j9_x, j9_y, j10_x, j10_y, j11_x, j11_y, j12_x, j12_y, j13_x, j13_y, j14_x, j14_y, j15_x, j15_y, j16_x, j16_y, j17_x, j17_y],...]

You can adapt those functions to read a .mat and output the same format array

666tua commented

Thank you very much for your reply!I downloaded the data set provided in your article.But I don't understand the contents of Y_test.txt and Y_train.txt.
a

666tua commented

它不需要任何特定的文件格式，只要 load_x 和 load_y 的输出是每帧 kpts 的二维数组，例如

[[j0_x, j0_y, j1_x, j1_y , j2_x, j2_y, j3_x, j3_y, j4_x, j4_y, j5_x, j5_y, j6_x, j6_y, j7_x, j7_y, j8_x, j8_y, j9_x, j9_y, j10_x, j10_y, j11_x, j11_y, j12_x, j12_y, j13_x, j13_y, j14_x, j14_y, j15_x, j15_y, j16_x, j16_y, j17_x, j17_y],...]

您可以调整这些函数以读取 .mat 并输出相同格式的数组

The content of X_train.txt is 18 pairs of coordinates. I want to know what the symbol in Y_train.txt means and how to make it.