SfMLearner
SfMLearner copied to clipboard
tinghuiz
An unsupervised learning framework for depth and ego-motion estimation from monocular videos
Hey, I wonder what's the loss level when you train from scratch? For me I followed the instruction in README to format KITTI data. When training from scratch the loss...
--------------------------------------------------------------------------- ValueError Traceback (most recent call last) in () 3 sfm.setup_inference(img_height, 4 img_width, ----> 5 mode='depth') /home/sk/Desktop/sfmNN/Untitled Folder/Untitled Folder/SfMLearner.pyc in setup_inference(self, img_height, img_width, mode, seq_length, batch_size) 311 self.batch_size = batch_size...
How many images can be processed per second using the trained network?
2018-05-03 11:50:18.112490: E tensorflow/core/util/events_writer.cc:104] Write failed because file could not be opened. Traceback (most recent call last): File "train.py", line 46, in tf.app.run() File "/home/chinmaya/.local/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 126, in run _sys.exit(main(argv))...
Hi I am a newbie in this field and trying to run SfMLearner. Your job is incredible. Thank you for sharing code. I have two question. 1. I checked out...
Hello, my hardware device is 16G+1080ti. When I use test_kitii_pose.py to test, seq_length = 5, and the fps is only 3. Is this normal? Is there any acceleration plan or...
The movement from this frame to the next frame should be to multiply the matrix to the current pose matrix, so theoretically, should the code be written as cam_to_world =...
Thanks for your share of work. Could you please provide codes of evaluation on Make3d dataset? Thanks very much.
