FilesExpand file tree

 master

/

SampleDecodeMultiThread.py

Copy path

Blame

More file actions

Blame

More file actions

Latest commit

 

History

History

History

160 lines (132 loc) · 5.89 KB

 master

/

SampleDecodeMultiThread.py

Copy path

Top

File metadata and controls

• Code
• Blame

160 lines (132 loc) · 5.89 KB

Raw

Copy raw file

Download raw file

Open symbols panel

Edit and raw actions

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

#

# Copyright 2020 NVIDIA Corporation

#

# 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.

#

# Starting from Python 3.8 DLL search policy has changed.

# We need to add path to CUDA DLLs explicitly.

import sys

import os

if os.name == 'nt':

# Add CUDA_PATH env variable

cuda_path = os.environ["CUDA_PATH"]

if cuda_path:

os.add_dll_directory(cuda_path)

else:

print("CUDA_PATH environment variable is not set.", file = sys.stderr)

print("Can't set CUDA DLLs search path.", file = sys.stderr)

exit(1)

# Add PATH as well for minor CUDA releases

sys_path = os.environ["PATH"]

if sys_path:

paths = sys_path.split(';')

for path in paths:

if os.path.isdir(path):

os.add_dll_directory(path)

else:

print("PATH environment variable is not set.", file = sys.stderr)

exit(1)

import pycuda.driver as cuda

import PyNvCodec as nvc

import numpy as np

from threading import Thread

class Worker(Thread):

def __init__(self, gpuID, encFile):

Thread.__init__(self)

# Retain primary CUDA device context and create separate stream per thread.

self.ctx = cuda.Device(gpuID).retain_primary_context()

self.ctx.push()

self.str = cuda.Stream()

self.ctx.pop()

# Create Decoder with given CUDA context & stream.

self.nvDec = nvc.PyNvDecoder(encFile, self.ctx.handle, self.str.handle)

width, height = self.nvDec.Width(), self.nvDec.Height()

hwidth, hheight = int(width / 2), int(height / 2)

# Determine colorspace conversion parameters.

# Some video streams don't specify these parameters so default values

# are most widespread bt601 and mpeg.

cspace, crange = self.nvDec.ColorSpace(), self.nvDec.ColorRange()

if nvc.ColorSpace.UNSPEC == cspace:

cspace = nvc.ColorSpace.BT_601

if nvc.ColorRange.UDEF == crange:

crange = nvc.ColorRange.MPEG

self.cc_ctx = nvc.ColorspaceConversionContext(cspace, crange)

print('Color space: ', str(cspace))

print('Color range: ', str(crange))

# Initialize colorspace conversion chain

if self.nvDec.ColorSpace() != nvc.ColorSpace.BT_709:

self.nvYuv = nvc.PySurfaceConverter(width, height, self.nvDec.Format(), nvc.PixelFormat.YUV420, self.ctx.handle, self.str.handle)

else:

self.nvYuv = None

if self.nvYuv:

self.nvCvt = nvc.PySurfaceConverter(width, height, self.nvYuv.Format(), nvc.PixelFormat.RGB, self.ctx.handle, self.str.handle)

else:

self.nvCvt = nvc.PySurfaceConverter(width, height, self.nvDec.Format(), nvc.PixelFormat.RGB, self.ctx.handle, self.str.handle)

self.nvRes = nvc.PySurfaceResizer(hwidth, hheight, self.nvCvt.Format(), self.ctx.handle, self.str.handle)

self.nvDwn = nvc.PySurfaceDownloader(hwidth, hheight, self.nvRes.Format(), self.ctx.handle, self.str.handle)

self.num_frame = 0

def run(self):

try:

while True:

try:

self.rawSurface = self.nvDec.DecodeSingleSurface()

if (self.rawSurface.Empty()):

print('No more video frames')

break

except nvc.HwResetException:

print('Continue after HW decoder was reset')

continue

if self.nvYuv:

self.yuvSurface = self.nvYuv.Execute(self.rawSurface, self.cc_ctx)

self.cvtSurface = self.nvCvt.Execute(self.yuvSurface, self.cc_ctx)

else:

self.cvtSurface = self.nvCvt.Execute(self.rawSurface, self.cc_ctx)

if (self.cvtSurface.Empty()):

print('Failed to do color conversion')

break

self.resSurface = self.nvRes.Execute(self.cvtSurface)

if (self.resSurface.Empty()):

print('Failed to resize surface')

break

self.rawFrame = np.ndarray(shape=(self.resSurface.HostSize()), dtype=np.uint8)

success = self.nvDwn.DownloadSingleSurface(self.resSurface, self.rawFrame)

if not (success):

print('Failed to download surface')

break

self.num_frame += 1

if(0 == self.num_frame % self.nvDec.Framerate()):

print(self.num_frame)

except Exception as e:

print(getattr(e, 'message', str(e)))

fout.close()

def create_threads(gpu_id, input_file, num_threads):

cuda.init()

thread_pool = []

for i in range(0, num_threads):

thread = Worker(gpu_id, input_file)

thread.start()

thread_pool.append(thread)

for thread in thread_pool:

thread.join()

if __name__ == "__main__":

print('This sample decodes video streams in parallel threads. It does not save output.')

print('GPU-accelerated color conversion and resize are also applied.')

print('This sample may serve as a stability test.')

print('Usage: python SampleDecodeMultiThread.py $gpu_id $input $num_threads')

if(len(sys.argv) < 4):

print("Provide input CLI arguments as shown above")

exit(1)

gpu_id = int(sys.argv[1])

input_file = sys.argv[2]

num_threads = int(sys.argv[3])

create_threads(gpu_id, input_file, num_threads)