Shreyz-max

def video_to_frames(video):
    path = os.path.join(config.test_path, 'temporary_images')
    if os.path.exists(path):
        shutil.rmtree(path)
    os.makedirs(path)
    video_path = os.path.join(config.test_path, 'video', video)
    count = 0
    image_list = []
    # Path to video file
    cap = cv2.VideoCapture(video_path)

Shreyz-max

def model_cnn_load():
    model = VGG16(weights="imagenet", include_top=True, input_shape=(224, 224, 3))
    out = model.layers[-2].output
    model_final = Model(inputs=model.input, outputs=out)
    return model_final


def load_image(path):
    img = cv2.imread(path)
    img = cv2.resize(img, (224, 224))

Shreyz-max

train_path='training_data'
TRAIN_LABEL_PATH = os.path.join(train_path, 'training_label.json')
# mentioning the train test split
train_split = 0.85
# loading the json file for training
with open(TRAIN_LABEL_PATH) as data_file:    
    y_data = json.load(data_file)
# train_list contains all the captions with their video ID
# vocab_list contains all the vocabulary from training data
train_list = []

Shreyz-max

"""
time_steps_encoder is the number of frames per video we will be using for training
num_encoder_tokens is the number of features from each frame
latent_dim is the number of hidden features for lstm
time_steps_decoder is the maximum length of each sentence
num_decoder_tokens is the final number of tokens in the softmax layer
batch size
"""
time_steps_encoder=80
num_encoder_tokens=4096

Shreyz-max

def load_datatest(train_path, epochs=100, x_data=x_data, tokenizer=tokenizer, num_decoder_tokens=1500,training_list=train_list, batch_size=32, maxlen=10):
    encoder_input_data = []
    decoder_input_data = []
    decoder_target_data = []
    videoId = []
    videoSeq = []
    # separating the videoId and the video captions
    for idx, cap in enumerate(training_list):
        caption = cap[0]
        videoId.append(cap[1])

Shreyz-max