MAT file required

[ashneg]

Fully pythonic branch doesn't works without the mat file

[prajwalkr]

Please post your exact error log here.

[ashneg]

Tried it with a still image. The log is below: python3 batch_inference.py --checkpoint_path ./logs/lipgan_residual_mel.h5 --face ../try.jpg --audio ../tryAudio.wav --results_dir ./results Using TensorFlow backend. /home/ashneg/.local/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:519: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_qint8 = np.dtype([("qint8", np.int8, 1)]) /home/ashneg/.local/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:520: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_quint8 = np.dtype([("quint8", np.uint8, 1)]) /home/ashneg/.local/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:521: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_qint16 = np.dtype([("qint16", np.int16, 1)]) /home/ashneg/.local/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:522: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_quint16 = np.dtype([("quint16", np.uint16, 1)]) /home/ashneg/.local/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:523: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. _np_qint32 = np.dtype([("qint32", np.int32, 1)]) /home/ashneg/.local/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:528: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'. np_resource = np.dtype([("resource", np.ubyte, 1)]) usage: batch_inference.py [-h] --checkpoint_path CHECKPOINT_PATH [--face_det_checkpoint FACE_DET_CHECKPOINT] --face FACE --audio AUDIO --mat MAT [--results_dir RESULTS_DIR] [--static STATIC] [--fps FPS] [--max_sec MAX_SEC] [--pads PADS [PADS ...]] [--face_det_batch_size FACE_DET_BATCH_SIZE] [--lipgan_batch_size LIPGAN_BATCH_SIZE] [--n_gpu N_GPU] batch_inference.py: error: the following arguments are required: --mat

[prajwalkr]

You are not using the code from the fully_pythonic branch. I rechecked and for this branch, --mat is not even an argument. Please switch branch to fully_pythonic after cloning the repo to resolve this issue. This instruction is present in the README as well.