You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This is a common problem, especially with drones. Add a sanity check to the image acquisition method that will generate a black image if your pipeline requires a continuous image stream, and you will lose a one or few frames but your pipeline won't break. Here's a sample code
responses = self.simGetImages([ImageRequest(0, ImageType.DepthPerspective, True, False)],vehicle_name)
if (responses[0] == None):
print("Camera is not returning image, please check airsim for error messages")
sys.exit(0)
img1d = np.array(responses[0].image_data_float, dtype=np.float)
img1d = 255/np.maximum(np.ones(img1d.size), img1d)
if (len(img1d) != (144*256)):
print('The depth camera returned bad data so Im creating zero array to not break the training')
img1d=np.ones(144*256)
img2d = np.reshape(img1d,(144, 256))```
Hi,
while collecting images I get some of them of size 0 B.
Does someone know why it happens and what can I do for not let this happening anymore?
Thanks in advance!!!
The text was updated successfully, but these errors were encountered: