Hello,

Thanks for the amazing work! :) I have been trying to run a test data. This is the error I am getting:

INFO:tensorflow:Error reported to Coordinator: <class 'tensorflow.python.framework.errors_impl.InvalidArgumentError'>, 2 root error(s) found.
  (0) Invalid argument: Expect 8 fields but have 13 in record 0
	 [[{{node DecodeCSV}}]]
	 [[IteratorGetNext]]
  (1) Invalid argument: Expect 8 fields but have 13 in record 0
	 [[{{node DecodeCSV}}]]
	 [[IteratorGetNext]]
	 [[IteratorGetNext/_231]]
0 successful operations.
0 derived errors ignored.
I0406 06:04:50.266259 139791091263232 coordinator.py:224] Error reported to Coordinator: <class 'tensorflow.python.framework.errors_impl.InvalidArgumentError'>, 2 root error(s) found.
  (0) Invalid argument: Expect 8 fields but have 13 in record 0
	 [[{{node DecodeCSV}}]]
	 [[IteratorGetNext]]
  (1) Invalid argument: Expect 8 fields but have 13 in record 0
	 [[{{node DecodeCSV}}]]
	 [[IteratorGetNext]]
	 [[IteratorGetNext/_231]]
0 successful operations.
0 derived errors ignored.
Traceback (most recent call last):
  File "test.py", line 399, in <module>
    tf.app.run()
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/platform/app.py", line 40, in run
    _run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
  File "/usr/local/lib/python2.7/dist-packages/absl/app.py", line 303, in run
    _run_main(main, args)
  File "/usr/local/lib/python2.7/dist-packages/absl/app.py", line 251, in _run_main
    sys.exit(main(argv))
  File "test.py", line 206, in main
    [ins, outs, jitter_outs, step] = sess.run([inputs, outputs, jitter_outputs, global_step])
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 950, in run
    run_metadata_ptr)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1173, in _run
    feed_dict_tensor, options, run_metadata)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1350, in _do_run
    run_metadata)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1370, in _do_call
    raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: 2 root error(s) found.
  (0) Invalid argument: Expect 8 fields but have 13 in record 0
	 [[{{node DecodeCSV}}]]
	 [[IteratorGetNext]]
  (1) Invalid argument: Expect 8 fields but have 13 in record 0
	 [[{{node DecodeCSV}}]]
	 [[IteratorGetNext]]
	 [[IteratorGetNext/_231]]
0 successful operations.
0 derived errors ignored.

Below is the command I have been using:

python test.py \
--cameras_glob '/home/DNN_Methods/Softwares/matryodshka-main/replica-6dof/6dof/apartment_0_6dof.txt' \
--image_dir '/home/DNN_Methods/Softwares/matryodshka-main/input/' \
--test_type on_video \
--input_type ODS \
--experiment_name matryodshka-with-transform-inverse-reg-checkpoint \
--checkpoint_dir '/home/DNN_Methods/Softwares/matryodshka-main/pretrained-models/' \
--output_root '/home/DNN_Methods/Softwares/matryodshka-main/trial_1/' \
--coord_net

Could you please tell me where it is going wrong?

Thanks very much! Any help would be much appreciated :)

Hello guys, thanks for sharing your code & data, but the latest commit in this repo is not working for me. By using the pertained model & Replica 360 Data that you released, the output PSV is all in single color which seems wrong. However, the commit 55df70335 works pretty well. So I guess that your latest commit maybe not match with your released model or data.

Hello @jamestompkin and @iszihan, I am a student currently working with spherical view synthesis. I would like to be able to make comparisons with MatryODShka but am using ERP images instead of ODS images. Would it be possible to also train MatryODShka with ERP images as input? If not, do you think it would be fair to instead create the 2 sphere volumes using 2 ERP images and projecting each to a location between them?

Hi @jamestompkin, thanks for your generous sharing, and I want to ask some questions: First, I came to notice that in another paperimmersive light field video with a layered mesh representation, they also use MSI features to train, are they the same one?

Second, as you guys use ODS images to train and the paper above use almost 50 images from different angles to train, I wonder whether can use some fisheye cameras(e.g, four located at the vertex of a square) to capture a dynamic scene and use your networks to train since fisheye cameras can also capture the same scene using fewer cameras compare to the above paper

Third, using four fisheye cameras can capture more details than your two ODS images, I wonder if these inputs can get better results?

Thanks very much for sharing the code. However, when I try to execute test.py with pre-trained models, I receive an error about checkpoint.

Exception has occurred: InvalidArgumentError Restoring from checkpoint failed. This is most likely due to a mismatch between the current graph and the graph from the checkpoint. Please ensure that you have not altered the graph expected based on the checkpoint. Original error:

Assign requires shapes of both tensors to match. lhs shape= [3,3,256,256] rhs shape= [3,3,257,256] [[node save/Assign_17 (defined at home/tuxiang/Documents/wjy/matryodshka-main/test.py:192) ]]

Errors may have originated from an input operation. Input Source operations connected to node save/Assign_17: net/conv3_1/weights (defined at home/tuxiang/Documents/wjy/matryodshka-main/matryodshka/nets.py:411)

It would be great if you could provide some insight for solving this issue.

Thank you very much.

Added wrap padding to MSI training network (note that it has not been added to the inference net). This helps reduce artifacts on the sides of result images/depthmaps. Also modified the ODS projection method to set out-of-bounds phi values to the top/bottom of the image to reduce pole artifacts in results.

I would like to try the code, but I can't find the "matryodshka-gpu.yml" so that I don't know the version of tensorflow and other package. Can you add the file into this repository？Thanks!