some trobule when i run the run_grasp_generator.py

[wuhuzi]

I am new guy in this research feild.I get some trobule when i run the run_grasp_generator.py.
I wish i could get your help.
Could you upload camera_pose.txt and camera_depth_scale.txt ?
Or tell me how to get these files in my environment. or tell us how to you make these files.
Actually, I don't understand this code in the grasp_generator.py :

Load camera pose and depth scale (from running calibration)

self.cam_pose = np.loadtxt('saved_data/camera_pose.txt', delimiter=' ')
self.cam_depth_scale = np.loadtxt('saved_data/camera_depth_scale.txt', delimiter=' ')
homedir = os.path.join(os.path.expanduser('~'), "grasp-comms")
self.grasp_request = os.path.join(homedir, "grasp_request.npy")
self.grasp_available = os.path.join(homedir, "grasp_available.npy")
self.grasp_pose = os.path.join(homedir, "grasp_pose.npy")

Thank you very much. Thanks for your time !

[skumra]

The information in camera_pose.txt and camera_depth_scale.txt depends on your hardware.

camera_pose.txt contains the pose of the camera in the robot frame.

camera_depth_scale.txt contains the depth scale of the camera. If there is no scaling factor required for the camera you are using, you can simply enter 1.0 in the file.

[wuhuzi]

Thanks for your reply. Nice work, Congratulations

[phideltaee]

I'm also looking into this file at the moment. Could you please explain what the file format of camera_pose.txt is? Is it a transform matrix?
In regards to the camera scaling, I've been trying to figure out what the gripper width scaling represents. If I run the realsense from further away, the grasp handle is still the same, but does not correspond the the 15cm gripper I'd expect. At what distance was this configured (for training and inferring)? I noticed that the method "post_process_output" from post_process.py has the width image scaled by 150.0, is that to account for normalization? Thank you for your help!

[Wuui-97]

@wuhuzi hello, could you upload camera_pose.txt? I have completed the camera calibration through other ways, can i make the file through the obtained transform matrix?

[deavn2236]

The information in camera_pose.txt and camera_depth_scale.txt depends on your hardware.

camera_pose.txt contains the pose of the camera in the robot frame.

camera_depth_scale.txt contains the depth scale of the camera. If there is no scaling factor required for the camera you are using, you can simply enter 1.0 in the file.

Hello, may I ask how you solved it? Could you please provide specific examples of camera_pose.txt and camera_depth_scale.txt files? I also use other methods for camera calibration, can I directly use them here