-
Notifications
You must be signed in to change notification settings - Fork 8
/
inference.py
executable file
·156 lines (138 loc) · 6.89 KB
/
inference.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
#!/usr/bin/env python2
#
# Copyright 1993-2018 NVIDIA Corporation. All rights reserved.
#
# NOTICE TO LICENSEE:
#
# This source code and/or documentation ("Licensed Deliverables") are
# subject to NVIDIA intellectual property rights under U.S. and
# international Copyright laws.
#
# These Licensed Deliverables contained herein is PROPRIETARY and
# CONFIDENTIAL to NVIDIA and is being provided under the terms and
# conditions of a form of NVIDIA software license agreement by and
# between NVIDIA and Licensee ("License Agreement") or electronically
# accepted by Licensee. Notwithstanding any terms or conditions to
# the contrary in the License Agreement, reproduction or disclosure
# of the Licensed Deliverables to any third party without the express
# written consent of NVIDIA is prohibited.
#
# NOTWITHSTANDING ANY TERMS OR CONDITIONS TO THE CONTRARY IN THE
# LICENSE AGREEMENT, NVIDIA MAKES NO REPRESENTATION ABOUT THE
# SUITABILITY OF THESE LICENSED DELIVERABLES FOR ANY PURPOSE. IT IS
# PROVIDED "AS IS" WITHOUT EXPRESS OR IMPLIED WARRANTY OF ANY KIND.
# NVIDIA DISCLAIMS ALL WARRANTIES WITH REGARD TO THESE LICENSED
# DELIVERABLES, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY,
# NONINFRINGEMENT, AND FITNESS FOR A PARTICULAR PURPOSE.
# NOTWITHSTANDING ANY TERMS OR CONDITIONS TO THE CONTRARY IN THE
# LICENSE AGREEMENT, IN NO EVENT SHALL NVIDIA BE LIABLE FOR ANY
# SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL DAMAGES, OR ANY
# DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
# WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
# ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
# OF THESE LICENSED DELIVERABLES.
#
# U.S. Government End Users. These Licensed Deliverables are a
# "commercial item" as that term is defined at 48 C.F.R. 2.101 (OCT
# 1995), consisting of "commercial computer software" and "commercial
# computer software documentation" as such terms are used in 48
# C.F.R. 12.212 (SEPT 1995) and is provided to the U.S. Government
# only as a commercial end item. Consistent with 48 C.F.R.12.212 and
# 48 C.F.R. 227.7202-1 through 227.7202-4 (JUNE 1995), all
# U.S. Government End Users acquire the Licensed Deliverables with
# only those rights set forth herein.
#
# Any use of the Licensed Deliverables in individual and commercial
# software must include, in the user documentation and internal
# comments to the code, the above Disclaimer and U.S. Government End
# Users Notice.
#
from __future__ import print_function
import time
import numpy as np
import tensorrt as trt
import pycuda.driver as cuda
import pycuda.autoinit
from PIL import ImageDraw
from data_processing import PreprocessYOLO, PostprocessYOLO, ALL_CATEGORIES, \
OUTPUT_SHAPES_DICT
import sys, os
import common
TRT_LOGGER = trt.Logger()
def draw_bboxes(image_raw, bboxes, confidences, categories, all_categories, bbox_color='red'):
"""Draw the bounding boxes on the original input image and return it.
Keyword arguments:
image_raw -- a raw PIL Image
bboxes -- NumPy array containing the bounding box coordinates of N objects, with shape (N,4).
categories -- NumPy array containing the corresponding category for each object,
with shape (N,)
confidences -- NumPy array containing the corresponding confidence for each object,
with shape (N,)
all_categories -- a list of all categories in the correct ordered (required for looking up
the category name)
bbox_color -- an optional string specifying the color of the bounding boxes (default: 'blue')
"""
draw = ImageDraw.Draw(image_raw)
print(bboxes, confidences, categories)
for box, score, category in zip(bboxes, confidences, categories):
x_coord, y_coord, width, height = box
left = max(0, np.floor(x_coord + 0.5).astype(int))
top = max(0, np.floor(y_coord + 0.5).astype(int))
right = min(image_raw.width, np.floor(x_coord + width + 0.5).astype(int))
bottom = min(image_raw.height, np.floor(y_coord + height + 0.5).astype(int))
draw.rectangle(((left, top), (right, bottom)), outline=bbox_color)
draw.text((left, top - 12), '{0} {1:.2f}'.format(all_categories[category], score), fill=bbox_color)
return image_raw
def get_engine(engine_file_path=""):
print("Reading engine from file {}".format(engine_file_path))
with open(engine_file_path, "rb") as f, trt.Runtime(TRT_LOGGER) as runtime:
return runtime.deserialize_cuda_engine(f.read())
def main():
# configure
INPUT_SIZE = 608
INPUT_LIST_FILE = './ped_list.txt'
SAVE_PATH = './images_results/'
ENGINE_FILE_PATH = './engines/engine_' + str(INPUT_SIZE) + '.trt'
filenames = []
with open(INPUT_LIST_FILE, 'r') as l:
lines = l.readlines()
for line in lines:
filename = line.strip()
filenames.append(filename)
input_resolution_yolov3_HW = (INPUT_SIZE, INPUT_SIZE)
preprocessor = PreprocessYOLO(input_resolution_yolov3_HW)
postprocessor_args = {"yolo_masks": [(3, 4, 5), (0, 1, 2)],
"yolo_anchors": [(8,34), (14,60), (23,94), (39,149), (87,291), (187,472)],
"obj_threshold": 0.1,
"nms_threshold": 0.3,
"yolo_input_resolution": input_resolution_yolov3_HW}
postprocessor = PostprocessYOLO(**postprocessor_args)
output_shapes = OUTPUT_SHAPES_DICT[str(INPUT_SIZE)]
with get_engine(ENGINE_FILE_PATH) as engine, engine.create_execution_context() as context:
inputs, outputs, bindings, stream = common.allocate_buffers(engine)
for filename in filenames:
image_raw, image = preprocessor.process(filename)
shape_orig_WH = image_raw.size
trt_outputs = []
# Do inference
print('Running inference on image {}...'.format(filename))
inputs[0].host = image
c_time = 0
t1 = time.time()
trt_outputs = common.do_inference(context, bindings=bindings, inputs=inputs, outputs=outputs, stream=stream)
t2 = time.time()
c_time = t2-t1
print('Inference takes time {}...'.format(c_time))
trt_outputs = [output.reshape(shape) for output, shape in zip(trt_outputs, output_shapes)]
boxes, classes, scores = postprocessor.process(trt_outputs, (shape_orig_WH))
if len(boxes) != 0:
obj_detected_img = draw_bboxes(image_raw, boxes, scores, classes, ALL_CATEGORIES)
else:
obj_detected_img = image_raw
savename_0 = filename.split('/')[-1]
savename = savename_0.split('.')[0]
output_image_path = SAVE_PATH + savename + '_' + str(INPUT_SIZE) + '.png'
obj_detected_img.save(output_image_path, 'PNG')
print('Saved image with bounding boxes of detected objects to {}.'.format(output_image_path))
if __name__ == '__main__':
main()