-
Notifications
You must be signed in to change notification settings - Fork 5
/
utility.py
210 lines (148 loc) · 7.14 KB
/
utility.py
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
209
210
import torch
import torch.nn as nn
import numpy as np
import cv2
device = "cuda:0" if torch.cuda.is_available() else "cpu"
class EmptyLayer(nn.Module):
def __init__(self):
super(EmptyLayer, self).__init__()
class DetectionLayer(nn.Module):
def __init__(self, anchors):
super(DetectionLayer, self).__init__()
self.anchors = anchors
def input_img():
image = cv2.imread("images/img2.jpg")
image = cv2.resize(image, (416, 416))
image = image[:, :, ::-1].transpose((2, 0, 1))
image = image[np.newaxis, :, :, :] / 255.0
image = torch.from_numpy(image).float()
return image
def unique(tensor):
tensor_np = tensor.cpu().numpy()
unique_np = np.unique(tensor_np)
unique_tensor = torch.from_numpy(unique_np)
tensor_res = tensor.new(unique_tensor.shape)
tensor_res.copy_(unique_tensor)
return tensor_res
def bbox_iou(box1, box2):
"""Calculating the IOU of given boxes"""
b1_x1, b1_y1, b1_x2, b1_y2 = box1[:,0], box1[:,1], box1[:,2], box1[:,3]
b2_x1, b2_y1, b2_x2, b2_y2 = box2[:,0], box2[:,1], box2[:,2], box2[:,3]
# get the coordinates of the intersection rectangle
inter_rect_x1 = torch.max(b1_x1, b2_x1)
inter_rect_y1 = torch.max(b1_y1, b2_y1)
inter_rect_x2 = torch.min(b1_x2, b2_x2)
inter_rect_y2 = torch.min(b1_y2, b2_y2)
# Intersection area
inter_area = torch.clamp(inter_rect_x2 - inter_rect_x1 + 1, min=0) * torch.clamp(inter_rect_y2 - inter_rect_y1 + 1, min=0)
# Union Area
b1_area = (b1_x2 - b1_x1 + 1)*(b1_y2 - b1_y1 + 1)
b2_area = (b2_x2 - b2_x1 + 1)*(b2_y2 - b2_y1 + 1)
iou = inter_area / (b1_area + b2_area - inter_area)
return iou
def transform_tensor(prediction, inp_dim, anchors, num_classes):
batch_size = prediction.size(0)
stride = inp_dim // prediction.size(2)
grid_size = inp_dim // stride
bbox_attrs = 5 + num_classes
num_anchors = len(anchors)
prediction = prediction.view(batch_size, bbox_attrs*num_anchors, grid_size*grid_size)
prediction = prediction.transpose(1,2).contiguous()
prediction = prediction.view(batch_size, grid_size*grid_size*num_anchors, bbox_attrs)
anchors = [(a[0]/stride, a[1]/stride) for a in anchors]
# passing the center coordinates through sigmoid
prediction[:,:,0] = torch.sigmoid(prediction[:,:,0])
prediction[:,:,1] = torch.sigmoid(prediction[:,:,1])
prediction[:,:,4] = torch.sigmoid(prediction[:,:,4])
# Adding offset to center
grid = np.arange(grid_size)
a,b = np.meshgrid(grid, grid)
x_offset = torch.FloatTensor(a).view(-1,1).to(device)
y_offset = torch.FloatTensor(b).view(-1,1).to(device)
x_y_offset = torch.cat((x_offset, y_offset), 1).repeat(1,num_anchors).view(-1,2).unsqueeze(0)
prediction[:,:,:2] += x_y_offset
anchors = torch.FloatTensor(anchors).to(device)
anchors = anchors.repeat(grid_size*grid_size, 1).unsqueeze(0)
prediction[:,:,2:4] = torch.exp(prediction[:,:,2:4])*anchors
prediction[:,:,5: 5 + num_classes] = torch.sigmoid((prediction[:,:, 5 : 5 + num_classes]))
prediction[:,:,:4] *= stride
return prediction
def write_results(prediction, confidence, num_classes, nms_conf = 0.4):
conf_mask = (prediction[:,:,4] > confidence).float().unsqueeze(2)
prediction = prediction*conf_mask
box_corner = prediction.new(prediction.shape)
box_corner[:,:,0] = (prediction[:,:,0] - prediction[:,:,2]/2)
box_corner[:,:,1] = (prediction[:,:,1] - prediction[:,:,3]/2)
box_corner[:,:,2] = (prediction[:,:,0] + prediction[:,:,2]/2)
box_corner[:,:,3] = (prediction[:,:,1] + prediction[:,:,3]/2)
prediction[:,:,:4] = box_corner[:,:,:4]
batch_size = prediction.size(0)
flag = False
for ind in range(batch_size):
image_pred = prediction[ind] # Image Tensor
max_conf, max_conf_score = torch.max(image_pred[:,5:5+ num_classes], 1)
max_conf = max_conf.float().unsqueeze(1)
max_conf_score = max_conf_score.float().unsqueeze(1)
seq = (image_pred[:,:5], max_conf, max_conf_score)
image_pred = torch.cat(seq, 1)
non_zero_ind = (torch.nonzero(image_pred[:,4]))
try:
image_pred_ = image_pred[non_zero_ind.squeeze(),:].view(-1,7)
except:
continue
if image_pred_.shape[0] == 0:
continue
# Get the various classes detected in the image
img_classes = unique(image_pred_[:,-1]) # last index(-1) holds the class index
for cls in img_classes:
cls_mask = image_pred_*(image_pred_[:,-1] == cls).float().unsqueeze(1)
class_mask_ind = torch.nonzero(cls_mask[:,-2]).squeeze()
image_pred_class = image_pred_[class_mask_ind].view(-1,7)
conf_sort_index = torch.sort(image_pred_class[:,4], descending = True )[1]
image_pred_class = image_pred_class[conf_sort_index]
idx = image_pred_class.size(0)
for i in range(idx):
try:
ious = bbox_iou(image_pred_class[i].unsqueeze(0), image_pred_class[i+1:])
except ValueError:
break
except IndexError:
break
# Zero out all the detections that have IoU > threshhold
iou_mask = (ious < nms_conf).float().unsqueeze(1)
image_pred_class[i+1:] *= iou_mask
# Remove the non-zero entries
non_zero_ind = torch.nonzero(image_pred_class[:,4]).squeeze()
image_pred_class = image_pred_class[non_zero_ind].view(-1,7)
batch_ind = image_pred_class.new(image_pred_class.size(0), 1).fill_(ind)
seq = batch_ind, image_pred_class
if not flag:
output = torch.cat(seq,1)
flag = True
else:
out = torch.cat(seq,1)
output = torch.cat((output,out))
try:
return output
except:
return 0
def resize_image(img, inp_dim):
"""Resize image with unchanged aspect ratio using padding"""
img_w, img_h = img.shape[1], img.shape[0]
w, h = inp_dim
new_w = int(img_w * min(w/img_w, h/img_h))
new_h = int(img_h * min(w/img_w, h/img_h))
resized_image = cv2.resize(img, (new_w,new_h), interpolation = cv2.INTER_CUBIC)
canvas = np.full((inp_dim[1], inp_dim[0], 3), 128)
canvas[(h-new_h)//2:(h-new_h)//2 + new_h,(w-new_w)//2:(w-new_w)//2 + new_w, :] = resized_image
return canvas
def prep_image(img, inp_dim):
"""Converting the numpy array into PyTorch tensor"""
img = (resize_image(img, (inp_dim, inp_dim)))
img = img[:,:,::-1].transpose((2,0,1)).copy()
img = torch.from_numpy(img).float().div(255.0).unsqueeze(0)
return img
def load_classes(namesfile):
fp = open(namesfile, "r")
names = fp.read().split("\n")[:-1]
return names