code_Rubbish_object_detection.zip

import random import numpy as np import cv2 import matplotlib.pyplot as plt import sys import os from bbox_util import * class RandomHorizontalFlip(object): """Randomly horizontally flips the Image with the probability *p* Parameters ---------- p: float The probability with which the image is flipped Returns ------- numpy.ndaaray Flipped image in the numpy format of shape `HxWxC` numpy.ndarray Tranformed bounding box co-ordinates of the format `n x 4` where n is number of bounding boxes and 4 represents `x1,y1,x2,y2` of the box """ def __init__(self, p=0.5): self.p = p def __call__(self, img, bboxes): img_center = np.array(img.shape[:2])[::-1]/2 img_center = np.hstack((img_center, img_center)) if random.random() < self.p: img = img[:, ::-1, :] bboxes[:, [0, 2]] += 2*(img_center[[0, 2]] - bboxes[:, [0, 2]]) box_w = abs(bboxes[:, 0] - bboxes[:, 2]) bboxes[:, 0] -= box_w bboxes[:, 2] += box_w return img, bboxes class HorizontalFlip(object): """Randomly horizontally flips the Image with the probability *p* Parameters ---------- p: float The probability with which the image is flipped Returns ------- numpy.ndaaray Flipped image in the numpy format of shape `HxWxC` numpy.ndarray Tranformed bounding box co-ordinates of the format `n x 4` where n is number of bounding boxes and 4 represents `x1,y1,x2,y2` of the box """ def __init__(self): pass def __call__(self, img, bboxes): img_center = np.array(img.shape[:2])[::-1]/2 img_center = np.hstack((img_center, img_center)) img = img[:, ::-1, :] bboxes[:, [0, 2]] += 2*(img_center[[0, 2]] - bboxes[:, [0, 2]]) box_w = abs(bboxes[:, 0] - bboxes[:, 2]) bboxes[:, 0] -= box_w bboxes[:, 2] += box_w return img, bboxes class RandomScale(object): """Randomly scales an image Bounding boxes which have an area of less than 25% in the remaining in the transformed image is dropped. The resolution is maintained, and the remaining area if any is filled by black color. Parameters ---------- scale: float or tuple(float) if **float**, the image is scaled by a factor drawn randomly from a range (1 - `scale` , 1 + `scale`). If **tuple**, the `scale` is drawn randomly from values specified by the tuple Returns ------- numpy.ndaaray Scaled image in the numpy format of shape `HxWxC` numpy.ndarray Tranformed bounding box co-ordinates of the format `n x 4` where n is number of bounding boxes and 4 represents `x1,y1,x2,y2` of the box """ def __init__(self, scale = 0.2, diff = False): self.scale = scale if type(self.scale) == tuple: assert len(self.scale) == 2, "Invalid range" assert self.scale[0] > -1, "Scale factor can't be less than -1" assert self.scale[1] > -1, "Scale factor can't be less than -1" else: assert self.scale > 0, "Please input a positive float" self.scale = (max(-1, -self.scale), self.scale) self.diff = diff def __call__(self, img, bboxes): #Chose a random digit to scale by img_shape = img.shape if self.diff: scale_x = random.uniform(*self.scale) scale_y = random.uniform(*self.scale) else: scale_x = random.uniform(*self.scale) scale_y = scale_x resize_scale_x = 1 + scale_x resize_scale_y = 1 + scale_y img= cv2.resize(img, None, fx = resize_scale_x, fy = resize_scale_y) bboxes[:,:4] *= [resize_scale_x, resize_scale_y, resize_scale_x, resize_scale_y] canvas = np.zeros(img_shape, dtype = np.uint8) y_lim = int(min(resize_scale_y,1)*img_shape[0]) x_lim = int(min(resize_scale_x,1)*img_shape[1]) canvas[:y_lim,:x_lim,:] = img[:y_lim,:x_lim,:] img = canvas bboxes = clip_box(bboxes, [0,0,1 + img_shape[1], img_shape[0]], 0.25) return img, bboxes class Scale(object): """Scales the image Bounding boxes which have an area of less than 25% in the remaining in the transformed image is dropped. The resolution is maintained, and the remaining area if any is filled by black color. Parameters ---------- scale_x: float The factor by which the image is scaled horizontally scale_y: float The factor by which the image is scaled vertically Returns ------- numpy.ndaaray Scaled image in the numpy format of shape `HxWxC` numpy.ndarray Tranformed bounding box co-ordinates of the format `n x 4` where n is number of bounding boxes and 4 represents `x1,y1,x2,y2` of the box """ def __init__(self, scale_x = 0.2, scale_y = 0.2): self.scale_x = scale_x self.scale_y = scale_y def __call__(self, img, bboxes): #Chose a random digit to scale by img_shape = img.shape resize_scale_x = 1 + self.scale_x resize_scale_y = 1 + self.scale_y img= cv2.resize(img, None, fx = resize_scale_x, fy = resize_scale_y) bboxes[:,:4] *= [resize_scale_x, resize_scale_y, resize_scale_x, resize_scale_y] canvas = np.zeros(img_shape, dtype = np.uint8) y_lim = int(min(resize_scale_y,1)*img_shape[0]) x_lim = int(min(resize_scale_x,1)*img_shape[1]) canvas[:y_lim,:x_lim,:] = img[:y_lim,:x_lim,:] img = canvas bboxes = clip_box(bboxes, [0,0,1 + img_shape[1], img_shape[0]], 0.25) return img, bboxes class RandomTranslate(object): """Randomly Translates the image Bounding boxes which have an area of less than 25% in the remaining in the transformed image is dropped. The resolution is maintained, and the remaining area if any is filled by black color. Parameters ---------- translate: float or tuple(float) if **float**, the image is translated by a factor drawn randomly from a range (1 - `translate` , 1 + `translate`). If **tuple**, `translate` is drawn randomly from values specified by the tuple Returns ------- numpy.ndaaray Translated image in the numpy format of shape `HxWxC` numpy.ndarray Tranformed bounding box co-ordinates of the format `n x 4` where n is number of bounding boxes and 4 represents `x1,y1,x2,y2` of the box """ def __init__(self, translate = 0.2, diff = False): self.translate = translate if type(self.translate) == tuple: assert len(self.translate) == 2, "Invalid range" assert self.translate[0] > 0 & self.translate[0] < 1 assert self.translate[1] > 0 & self.translate[1] < 1 else: assert self.translate > 0 and self.translate < 1 self.translate = (-self.translate, self.translate) self.diff = diff def __call__(self, img, bboxes): #Chose a random digit to scale by img_shape = img.shape #translate the image #percentage of the dimension of the image to translate translate_factor_x = random.uniform(*self.translate) tr