**UnknownError: JIT compilation failed. [Op:Sub] **
I am trying to make a lip reading model but it's giving me the following error:
UnknownError Traceback (most recent call last)
Cell In[16], line 1
----> 1 frames,alignments=load_data(tf.convert_to_tensor(test_path))
Cell In[13], line 6, in load_data(path)
4 video_path=os.path.join('data','s1',f'{file_name}.mpg')
5 align_path=os.path.join('data','alignments','s1',f'{file_name}.align')
----> 6 frames=load_vid(video_path)
7 alignments=load_alignments(align_path)
9 return frames,alignments
Cell In[6], line 11, in load_vid(path)
9 mean=tf.math.reduce_mean(frames)
10 std=tf.math.reduce_std(tf.cast(frames,tf.float32))
---> 11 return tf.cast((frames-mean),tf.float32)/std
load_data function:
def load_data(path: str):
path=bytes.decode(path.numpy())
file_name=path.split('\\')[-1].split('.')[0] #grabbing file name
video_path=os.path.join('data','s1',f'{file_name}.mpg')
align_path=os.path.join('data','alignments','s1',f'{file_name}.align')
frames=load_vid(video_path)
alignments=load_alignments(align_path)
return frames,alignments
load_alignments function:
def load_alignments(path: str)->List[str]:
with open(path,'r') as f:
lines=f.readlines()
tokens=[]
for line in lines:
line=line.split()
if line[2] !='sil':
tokens=[*tokens,' ',line[2]]
return char_to_no(tf.reshape(tf.strings.unicode_split(tokens,input_encoding='UTF-8'),(-1)))[1:]
and at the end it says : UnknownError: JIT compilation failed. [Op:Sub]
