I generated a data-set of (200 x 200x 3) images in which each image contains a 40 X 40 box of different color.
Create a model using tensorflow which can predict coords of this 40 x 40 box.
The code i used for generating these images:
from PIL import Image, ImageDraw
from random import randrange
The code i used for generating these images:
from PIL import Image, ImageDraw from random import randrange
colors = ["#ffd615", "#f9ff21", "#00d1ff", "#0e153a", "#fc5c9c", "#ac3f21", "#40514e", "#492540", "#ff8a5c", "#000000", "#a6fff2", "#f0f696", "#d72323", "#dee1ec", "#fcb1b1"]
def genrate_image(color): img = Image.new(mode="RGB", size=(200, 200), color=color) return img
def save_image(img, imgname): img.save(imgname)
def draw_rect(image, color, x, y): draw = ImageDraw.Draw(image) coords = ((x, y), (x+40, y), (x+40, y+40), (x, y+40)) draw.polygon(coords, fill=color)
return image, str(coords)
FILE_NAME = "train_annotations.txt"
for i in range(0, 100): img = genrate_image(colors[randrange(0, len(colors))]) img, x0, x1, y0, y1 = draw_rect(img, colors[randrange(0, len(colors))], randrange(200 - 50), randrange(200 - 50)) save_image(img, "dataset/train_images/img"+str(i)+".png") with open(FILE_NAME, "a+") as f: f.write(f"{x0} {x1} {y0} {y1}\n") f.close()