Spaces:
Running
Running
File size: 8,269 Bytes
e6748e7 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 |
import cv2
import matplotlib.pyplot as plt
import numpy as np
import torch
from PIL import Image
def segment_everything(_input, model, device, input_size=1024, iou_threshold=0.7, conf_threshold=0.25, better_quality=False, contour_thickness=1, max_det = 500):
"""
Performs segmentation on the input image and returns the segmented image and annotations.
"""
input_image = _input
input_size = int(input_size)
w, h = input_image.size
scale = input_size / max(w, h)
new_w = int(w * scale)
new_h = int(h * scale)
input_image = input_image.resize((new_w, new_h))
results = model(input_image,
retina_masks=True,
iou=iou_threshold,
conf=conf_threshold,
imgsz=input_size,
max_det=max_det)
annotations = results[0].masks.data
segmented_image = fast_process(annotations=annotations,
device=device,
image=input_image,
scale=(1024 // input_size),
better_quality=better_quality,
contour_thickness=contour_thickness)
return segmented_image, annotations
def fast_process(annotations,
image,
device,
scale,
better_quality=False,
mask_random_color=True,
bbox=None,
use_retina=True,
withContours=True,
contour_thickness=2):
if isinstance(annotations[0], dict):
annotations = [annotation['segmentation'] for annotation in annotations]
original_h = image.height
original_w = image.width
if better_quality:
if isinstance(annotations[0], torch.Tensor):
annotations = np.array(annotations.cpu())
for i, mask in enumerate(annotations):
mask = cv2.morphologyEx(mask.astype(np.uint8), cv2.MORPH_OPEN, np.ones((3, 3), np.uint8))
annotations[i] = cv2.morphologyEx(mask.astype(np.uint8), cv2.MORPH_OPEN, np.ones((8, 8), np.uint8))
if device == 'cpu':
annotations = np.array(annotations)
inner_mask = fast_show_mask(
annotations,
plt.gca(),
random_color=mask_random_color,
bbox=bbox,
retinamask=use_retina,
target_height=original_h,
target_width=original_w,
)
else:
if isinstance(annotations[0], np.ndarray):
annotations = torch.from_numpy(annotations)
inner_mask = fast_show_mask_gpu(
annotations,
plt.gca(),
random_color=mask_random_color,
bbox=bbox,
retinamask=use_retina,
target_height=original_h,
target_width=original_w,
)
if isinstance(annotations, torch.Tensor):
annotations = annotations.cpu().numpy()
kernel = np.ones((5, 5), np.uint8)
if withContours:
contour_all = []
temp = np.zeros((original_h, original_w, 1))
for i, mask in enumerate(annotations):
if type(mask) == dict:
mask = mask['segmentation']
annotation = mask.astype(np.uint8)
# Perform morphological operations for separating connected objects and smoothing contours
kernel = np.ones((5, 5), np.uint8)
annotation = cv2.morphologyEx(annotation, cv2.MORPH_OPEN, kernel)
annotation = cv2.GaussianBlur(annotation, (5, 5), 0)
# Find contours
contours, _ = cv2.findContours(annotation, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
for contour in contours:
hull = cv2.convexHull(contour)
epsilon = 0.005 * cv2.arcLength(contour, True)
approx = cv2.approxPolyDP(contour, epsilon, True)
contour_all.append(approx)
for i, contour in enumerate(contour_all):
M = cv2.moments(contour)
if M["m00"] != 0:
cX = int(M["m10"] / M["m00"])
cY = int(M["m01"] / M["m00"])
else:
cX, cY = 0, 0
cv2.putText(temp, str(i), (cX, cY), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 125, 255), 2)
cv2.drawContours(temp, contour_all, -1, (255, 255, 255), contour_thickness)
color = np.array([255 / 255, 0 / 255, 0 / 255, 1]) # RGBA
contour_mask = temp / 255 * color.reshape(1, 1, -1)
image = image.convert('RGBA')
overlay_inner = Image.fromarray((inner_mask * 255).astype(np.uint8), 'RGBA')
image.paste(overlay_inner, (0, 0), overlay_inner)
if withContours:
overlay_contour = Image.fromarray((contour_mask * 255).astype(np.uint8), 'RGBA')
image.paste(overlay_contour, (0, 0), overlay_contour)
return image
# CPU post process
def fast_show_mask(
annotation,
ax,
random_color=False,
bbox=None,
retinamask=True,
target_height=960,
target_width=960,
):
mask_sum = annotation.shape[0]
height = annotation.shape[1]
weight = annotation.shape[2]
# Sort annotation by area
areas = np.sum(annotation, axis=(1, 2))
sorted_indices = np.argsort(areas)[::1]
annotation = annotation[sorted_indices]
index = (annotation != 0).argmax(axis=0)
if random_color:
color = np.random.random((mask_sum, 1, 1, 3))
else:
color = np.ones((mask_sum, 1, 1, 3)) * np.array([30 / 255, 144 / 255, 255 / 255])
transparency = np.ones((mask_sum, 1, 1, 1)) * 0.6
visual = np.concatenate([color, transparency], axis=-1)
mask_image = np.expand_dims(annotation, -1) * visual
mask = np.zeros((height, weight, 4))
h_indices, w_indices = np.meshgrid(np.arange(height), np.arange(weight), indexing='ij')
indices = (index[h_indices, w_indices], h_indices, w_indices, slice(None))
mask[h_indices, w_indices, :] = mask_image[indices]
if bbox is not None:
x1, y1, x2, y2 = bbox
ax.add_patch(plt.Rectangle((x1, y1), x2 - x1, y2 - y1, fill=False, edgecolor='b', linewidth=1))
if not retinamask:
mask = cv2.resize(mask, (target_width, target_height), interpolation=cv2.INTER_NEAREST)
return mask
def fast_show_mask_gpu(
annotation,
ax,
random_color=False,
bbox=None,
retinamask=True,
target_height=960,
target_width=960,
):
device = annotation.device
mask_sum = annotation.shape[0]
height = annotation.shape[1]
weight = annotation.shape[2]
areas = torch.sum(annotation, dim=(1, 2))
sorted_indices = torch.argsort(areas, descending=False)
annotation = annotation[sorted_indices]
# Find the first non-zero value index for each position
index = (annotation != 0).to(torch.long).argmax(dim=0)
if random_color:
color = torch.rand((mask_sum, 1, 1, 3)).to(device)
else:
color = torch.ones((mask_sum, 1, 1, 3)).to(device) * torch.tensor(
[30 / 255, 144 / 255, 255 / 255]
).to(device)
transparency = torch.ones((mask_sum, 1, 1, 1)).to(device) * 0.6
visual = torch.cat([color, transparency], dim=-1)
mask_image = torch.unsqueeze(annotation, -1) * visual
# Use vectorization to get the value of the batch
mask = torch.zeros((height, weight, 4)).to(device)
h_indices, w_indices = torch.meshgrid(torch.arange(height), torch.arange(weight))
indices = (index[h_indices, w_indices], h_indices, w_indices, slice(None))
# Use vectorized indexing to update the show values
mask[h_indices, w_indices, :] = mask_image[indices]
mask_cpu = mask.cpu().numpy()
if bbox is not None:
x1, y1, x2, y2 = bbox
ax.add_patch(
plt.Rectangle(
(x1, y1), x2 - x1, y2 - y1, fill=False, edgecolor="b", linewidth=1
)
)
if not retinamask:
mask_cpu = cv2.resize(
mask_cpu, (target_width, target_height), interpolation=cv2.INTER_NEAREST
)
return mask_cpu
|