I have a dataframe which looks like this:
I'm building a model which takes text and video as input. So, my aim is to load the Text
and Media_location
(which contains video files path) from the dataframe, so that it is iterable when I feed df['Text']
and the video (loaded from path df['Media_location']
) together.
I couldn't find any implemenations in tensorflow that would do this sort of thing, so drop any suggestions you may have.
CodePudding user response:
You can try using tensorflow-io
, which will run in graph mode. Just run pip install tensorflow-io
and then try:
import tensorflow as tf
import tensorflow_io as tfio
import pandas as pd
df = pd.DataFrame(data={'Text': ['some text', 'some more text'],
'Media_location': ['/content/sample-mp4-file.mp4', '/content/sample-mp4-file.mp4']})
dataset = tf.data.Dataset.from_tensor_slices((df['Text'], df['Media_location']))
def decode_videos(x, y):
video = tf.io.read_file(y)
video = tfio.experimental.ffmpeg.decode_video(video)
return x, video
dataset = dataset.map(decode_videos)
for x, y in dataset:
print(x, y.shape)
tf.Tensor(b'some text', shape=(), dtype=string) (901, 270, 480, 3)
tf.Tensor(b'some more text', shape=(), dtype=string) (901, 270, 480, 3)
In this example, each video contains 901 frames.
If you are a Windows
users, you can try using cv2
like this:
import tensorflow as tf
import pandas as pd
from cv2 import cv2
import numpy as np
df = pd.DataFrame(data={'Text': ['some text', 'some more text'],
'Media_location': ['/content/sample-mp4-file.mp4', '/content/sample-mp4-file.mp4']})
dataset = tf.data.Dataset.from_tensor_slices((df['Text'], df['Media_location']))
def get_video_asarray(path):
frames = []
cap = cv2.VideoCapture(path.numpy().decode("utf-8"))
read = True
while read:
read, img = cap.read()
if read:
frames.append(img)
return np.stack(frames, axis=0)
def decode_videos(x, y):
y = tf.py_function(get_video_asarray, [y], Tout=[tf.float32])
return x, tf.squeeze(y, axis=0)
dataset = dataset.map(decode_videos)
for x, y in dataset:
print(x, y.shape)
tf.Tensor(b'some text', shape=(), dtype=string) (901, 270, 480, 3)
tf.Tensor(b'some more text', shape=(), dtype=string) (901, 270, 480, 3)
CodePudding user response:
You can use tensorflow.keras.utils.Sequence
.
import math
from tensorflow.keras.utils import Sequence
class Dataloader(Sequence):
def __init__(self, df, y_array, batch_size):
self.df, self.y_array = df, y_array
self.batch_size = batch_size
def __len__(self):
return math.ceil(len(self.df) / self.batch_size)
def __getitem__(self, idx):
slices = slice(idx*self.batch_size, (idx 1)*self.batch_size, None)
return [(tuple(a), b) for a, b in zip(self.df[['Text', 'Media_location']].iloc[slices].values, self.y_array[slices])]
example:
import numpy as np
for batch in Dataloader(df, np.random.randint(0, 2, size=10), 3):
for (text, video), label in batch:
print((text, video), label)
print()
output:
('E DDC', 'Videos\\17.mp4') 0
('CBAD ', 'Videos\\80.mp4') 1
('EBBBBB E', 'Videos\\07.mp4') 1
('ABB B ', 'Videos\\68.mp4') 0
('BCDADDA A', 'Videos\\73.mp4') 1
('CDECECADE', 'Videos\\04.mp4') 1
('EADBDBC', 'Videos\\85.mp4') 1
('ABCCBC AA', 'Videos\\50.mp4') 1
('DEBCA', 'Videos\\32.mp4') 1
('DD CCCB', 'Videos\\24.mp4') 0