miladfa7

import numpy as np
import os 
import cv2
import torchvision
import torch
import json 



def numpy_nms(boxes, scores, iou_threshold):

miladfa7

file="/mnt/disk2/users/milad/videos/final_match.mp4"
output_dir="/mnt/disk2/users/milad/output"

input_file="$file"
filename=$(basename -- "$input_file")
filename_noext="${filename%.*}"
output_file="$output_dir/${filename_noext}.mp4"

# Reduce video size using ffmpeg

miladfa7

import cv2
improt numpy as np 

def draw_rotated_text(image: np.ndarray, main_text: str) -> np.ndarray:
    main_font_face = cv2.FONT_HERSHEY_SIMPLEX
    main_font_scale = 0.4
    main_thickness = 1
    main_text_size, _ = cv2.getTextSize(main_text, main_font_face, main_font_scale, main_thickness)
    main_baseline = main_text_size[1] + main_thickness
    

miladfa7

# pip install pycocotools
from pycocotools.coco import COCO
import json

def merge_coco_json(json_files, output_file):
    merged_annotations = {
        "info": {},
        "licenses": [],
        "images": [],
        "annotations": [],

miladfa7

import io
import base64
from IPython.display import HTML

video = io.open('21590891783.mp4', 'r+b').read()
encoded = base64.b64encode(video)

HTML(data='''
<video controls>
    <source src="data:video/mp4;base64,{0}" type="video/mp4" />

miladfa7

from PIL import Image
from PIL import ImageOps
import os
import random

# set the path to the directory containing the images
input_path = "/path/.../input"
output_path = "/path/.../output"

# loop through each image file in the directory

miladfa7

import tensorflow as tf
from gensim.corpora import WikiCorpus
import os
import argparse

# lang = 'fa' farsi

def store(corpus, lang):
    base_path = os.getcwd()
    store_path = os.path.join(base_path, '{}_corpus'.format(lang))

miladfa7

from simpletransformers.language_modeling import LanguageModelingModel
import logging


logging.basicConfig(level=logging.INFO)
transformers_logger = logging.getLogger("transformers")
transformers_logger.setLevel(logging.WARNING)


train_args = {

miladfa7

import tensorflow 
from tensorflow.keras.preprocessing.image import ImageDataGenerator

# Create training ImageDataGenerator object
train_data_gen = ImageDataGenerator(rotation_range=50,
                                    width_shift_range=0.2,
                                    height_shift_range=0.2,
                                    zoom_range=0.3,
                                    horizontal_flip=True,
                                    vertical_flip=True,

miladfa7

import tensorflow 
from PIL import Image
import glob
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.preprocessing.image import img_to_array
from tensorflow.keras.preprocessing.image import load_img
import numpy as np

aug = ImageDataGenerator(
	rotation_range=30,