prateekjoshi565

from PIL import Image, ImageDraw, ImageFont
import matplotlib.pyplot as plt
import io

prateekjoshi565

# generate video
create_video_from_images("/images", "out.mp4")

prateekjoshi565

def create_video_from_images(images_folder, output_video, fps=10, duration=6):
    images = sorted(os.listdir(images_folder))

    # create path to the input images
    img_path = os.path.join(images_folder, images[0])
    
    # load image
    frame = cv2.imread(img_path)
    # extract dimensions of the image
    height, width, channels = frame.shape

prateekjoshi565

import cv2 # (OpenCV) version - 4.7.0
import os

prateekjoshi565

cnt = 0

for img in tqdm_notebook(col_images):
  
  # apply frame mask
  masked = cv2.bitwise_and(img[:,:,0], img[:,:,0], mask=stencil)
  
  # apply image thresholding
  ret, thresh = cv2.threshold(masked, 130, 145, cv2.THRESH_BINARY)

prateekjoshi565

# specify frame index
idx = 457

# plot frame
plt.figure(figsize=(10,10))
plt.imshow(col_images[idx][:,:,0], cmap= "gray")
plt.show()

prateekjoshi565

def get_relation(sent):

  doc = nlp(sent)

  # Matcher class object 
  matcher = Matcher(nlp.vocab)

  #define the pattern 
  pattern = [{'DEP':'ROOT'}, 
            {'DEP':'prep','OP':"?"},

prateekjoshi565

# remove punctuation marks
punctuation = '!"#$%&()*+-/:;<=>?@[\\]^_`{|}~'

train['clean_tweet'] = train['clean_tweet'].apply(lambda x: ''.join(ch for ch in x if ch not in set(punctuation)))
test['clean_tweet'] = test['clean_tweet'].apply(lambda x: ''.join(ch for ch in x if ch not in set(punctuation)))

# convert text to lowercase
train['clean_tweet'] = train['clean_tweet'].str.lower()
test['clean_tweet'] = test['clean_tweet'].str.lower()

prateekjoshi565

# extract subject
source = [i[0] for i in entity_pairs]

# extract object
target = [i[1] for i in entity_pairs]

kg_df = pd.DataFrame({'source':source, 'target':target, 'edge':relations})

prateekjoshi565

# predict next token
def predict(net, tkn, h=None):
         
  # tensor inputs
  x = np.array([[token2int[tkn]]])
  inputs = torch.from_numpy(x)
  
  # push to GPU
  inputs = inputs.cuda()