/
onnx_to_tensorrt.py
211 lines (185 loc) · 8.44 KB
/
onnx_to_tensorrt.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
211
#!/usr/bin/env python3
#
# SPDX-FileCopyrightText: Copyright (c) 1993-2024 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
from __future__ import print_function
import os
import sys
import numpy as np
import tensorrt as trt
from data_processing import ALL_CATEGORIES, PostprocessYOLO, PreprocessYOLO
from PIL import ImageDraw
sys.path.insert(1, os.path.join(sys.path[0], ".."))
from downloader import getFilePath
import common
TRT_LOGGER = trt.Logger()
def draw_bboxes(
image_raw, bboxes, confidences, categories, all_categories, bbox_color="blue"
):
"""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(onnx_file_path, engine_file_path=""):
"""Attempts to load a serialized engine if available, otherwise builds a new TensorRT engine and saves it."""
def build_engine():
"""Takes an ONNX file and creates a TensorRT engine to run inference with"""
with trt.Builder(TRT_LOGGER) as builder, builder.create_network(
0
) as network, builder.create_builder_config() as config, trt.OnnxParser(
network, TRT_LOGGER
) as parser, trt.Runtime(
TRT_LOGGER
) as runtime:
config.set_memory_pool_limit(
trt.MemoryPoolType.WORKSPACE, 1 << 28
) # 256MiB
# Parse model file
if not os.path.exists(onnx_file_path):
print(
"ONNX file {} not found, please run yolov3_to_onnx.py first to generate it.".format(
onnx_file_path
)
)
exit(0)
print("Loading ONNX file from path {}...".format(onnx_file_path))
with open(onnx_file_path, "rb") as model:
print("Beginning ONNX file parsing")
if not parser.parse(model.read()):
print("ERROR: Failed to parse the ONNX file.")
for error in range(parser.num_errors):
print(parser.get_error(error))
return None
# The actual yolov3.onnx is generated with batch size 64. Reshape input to batch size 1
network.get_input(0).shape = [1, 3, 608, 608]
print("Completed parsing of ONNX file")
print(
"Building an engine from file {}; this may take a while...".format(
onnx_file_path
)
)
plan = builder.build_serialized_network(network, config)
engine = runtime.deserialize_cuda_engine(plan)
print("Completed creating Engine")
with open(engine_file_path, "wb") as f:
f.write(plan)
return engine
if os.path.exists(engine_file_path):
# If a serialized engine exists, use it instead of building an engine.
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())
else:
return build_engine()
def main():
"""Create a TensorRT engine for ONNX-based YOLOv3-608 and run inference."""
# Try to load a previously generated YOLOv3-608 network graph in ONNX format:
onnx_file_path = "yolov3.onnx"
engine_file_path = "yolov3.trt"
# Download a dog image and save it to the following file path:
input_image_path = getFilePath("samples/python/yolov3_onnx/dog.jpg")
# Two-dimensional tuple with the target network's (spatial) input resolution in HW ordered
input_resolution_yolov3_HW = (608, 608)
# Create a pre-processor object by specifying the required input resolution for YOLOv3
preprocessor = PreprocessYOLO(input_resolution_yolov3_HW)
# Load an image from the specified input path, and return it together with a pre-processed version
image_raw, image = preprocessor.process(input_image_path)
# Store the shape of the original input image in WH format, we will need it for later
shape_orig_WH = image_raw.size
# Output shapes expected by the post-processor
output_shapes = [(1, 255, 19, 19), (1, 255, 38, 38), (1, 255, 76, 76)]
# Do inference with TensorRT
trt_outputs = []
with get_engine(
onnx_file_path, engine_file_path
) as engine, engine.create_execution_context() as context:
inputs, outputs, bindings, stream = common.allocate_buffers(engine)
# Do inference
print("Running inference on image {}...".format(input_image_path))
# Set host input to the image. The common.do_inference function will copy the input to the GPU before executing.
inputs[0].host = image
trt_outputs = common.do_inference(
context,
engine=engine,
bindings=bindings,
inputs=inputs,
outputs=outputs,
stream=stream,
)
# Before doing post-processing, we need to reshape the outputs as the common.do_inference will give us flat arrays.
trt_outputs = [
output.reshape(shape) for output, shape in zip(trt_outputs, output_shapes)
]
postprocessor_args = {
"yolo_masks": [
(6, 7, 8),
(3, 4, 5),
(0, 1, 2),
], # A list of 3 three-dimensional tuples for the YOLO masks
"yolo_anchors": [
(10, 13),
(16, 30),
(33, 23),
(30, 61),
(62, 45), # A list of 9 two-dimensional tuples for the YOLO anchors
(59, 119),
(116, 90),
(156, 198),
(373, 326),
],
"obj_threshold": 0.6, # Threshold for object coverage, float value between 0 and 1
"nms_threshold": 0.5, # Threshold for non-max suppression algorithm, float value between 0 and 1
"yolo_input_resolution": input_resolution_yolov3_HW,
}
postprocessor = PostprocessYOLO(**postprocessor_args)
# Run the post-processing algorithms on the TensorRT outputs and get the bounding box details of detected objects
boxes, classes, scores = postprocessor.process(trt_outputs, (shape_orig_WH))
# Draw the bounding boxes onto the original input image and save it as a PNG file
obj_detected_img = draw_bboxes(image_raw, boxes, scores, classes, ALL_CATEGORIES)
output_image_path = "dog_bboxes.png"
obj_detected_img.save(output_image_path, "PNG")
print(
"Saved image with bounding boxes of detected objects to {}.".format(
output_image_path
)
)
# Free host and device memory used for inputs and outputs
common.free_buffers(inputs, outputs, stream)
if __name__ == "__main__":
main()