acvictor / obama-lip-sync Goto Github PK

trying to run the example (after downloading all the relevant data) and getting this error:

ValueError: Error when checking input: expected lstm_1_input to have shape (50, 39) but got array with shape (10L, 39L)

Those where the log on output before the exception:

data/sampleAudio.wav
16000
('Shapes:', (5201L, 10L, 39L))
('Shapes:', (52010L, 39L))

Hi acvictor,
Could u plz tell me how to produce TestVideo/kp_test.pickle in run.py ?
Thank ya.

Hi acvictor. As far as I understand, 25 .wav files are used in the audioFeatures.py file for feature extraction. I could not find these files anywhere. I thought that they were converted from mp4 files, in the rawData folder, to wav files but there are only 11 mp4 files in there. Is it possible for you to share these wav files? I would be very appreciated if you could help.

Thanks for this helpful repository.

Traceback (most recent call last):
File "pix2pix.py", line 805, in
main()
File "pix2pix.py", line 627, in main
examples = load_examples()
File "pix2pix.py", line 261, in load_examples
reader = tf.WholeFileReader()
AttributeError: module 'tensorflow' has no attribute 'WholeFileReader'

possible to get better results with pix2pixHD or vid2vid https://github.com/NVIDIA/pix2pixHD or https://github.com/NVIDIA/vid2vid

while running this in colab
!python run.py --sf sampleAudio.wav --mf path/obama.h5 --lb 10

getting this error
IOError: Unable to open file (unable to open file: name = 'obama.h5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0)

Sir,I am trying to run your to code and train the network but I don't understand. Can you make a good readme file for whole train process and a doc for file structure. I will help me a lot.

Thank You.

When I run the run.py I'm getting this error
The syntax of the command is incorrect.
Traceback (most recent call last):
File "run.py", line 41, in
model = load_model(modelFile)
File "C:\Users\hp-user\Anaconda3\envs\tensorflow_env\lib\site-packages\keras\engine\saving.py", line 417, in load_model
f = h5dict(filepath, 'r')
File "C:\Users\hp-user\Anaconda3\envs\tensorflow_env\lib\site-packages\keras\utils\io_utils.py", line 186, in init
self.data = h5py.File(path, mode=mode)
File "C:\Users\hp-user\Anaconda3\envs\tensorflow_env\lib\site-packages\h5py_hl\files.py", line 394, in init
swmr=swmr)
File "C:\Users\hp-user\Anaconda3\envs\tensorflow_env\lib\site-packages\h5py_hl\files.py", line 170, in make_fid
fid = h5f.open(name, flags, fapl=fapl)
File "h5py_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
File "h5py_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
File "h5py\h5f.pyx", line 85, in h5py.h5f.open
OSError: Unable to open file (unable to open file: name = 'path/obama.h5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0)

Hello!Could you upload obama.h5 and checkpoint file again?Please.Thank you!
Link of trained model in your goole drive were closed.
Or Could you tell me where I can get this?

FileNotFoundError: [Errno 2] No such file or directory: 'Pix2PixModel/options.json'

I have no the file. where could i find it?

Pix2Pix project is not available in this link: https://drive.google.com/file/d/1xVD2qjyJodTbO3c_-14zwPF5ctwLAFYp/view
Is there any other link to download Pix2Pix project?

can you please provide the pretrained obama.h5 file, it was not in the pix2pix model dir

Without the premade pix2pix model originally used in this repo, I have to make my own model.
How can I put the points given in the map "rawData" to the images of Obama with the mouth cut out?
similar to the frames of "results/input500ms.mp4"

Alternatively, could you upload your own pix2pix model?

requirements.txt ????