def generate_data(filename, version, block_size=16):
input_path = os.path.join(PGM_ORIGINAL_PATH, filename + PGM_SUFFIX)
if not os.path.exists(BITSTREAM_PATH):
os.mkdir(BITSTREAM_PATH)
bitstream_path = os.path.join(BITSTREAM_PATH, filename + BITSTREAM_SUFFIX)
if not os.path.exists(PGM_RECONSTRUCTION_PATH):
os.mkdir(PGM_RECONSTRUCTION_PATH)
output_path = os.path.join(PGM_RECONSTRUCTION_PATH, filename + PGM_SUFFIX)
df = pd.DataFrame(columns=['bpp', 'db'])
for index, quality in enumerate([8, 12, 16, 20, 24]):
enc = Encoder(input_path, bitstream_path, block_size, quality, False)
enc.encode_image()
dec = Decoder(bitstream_path, output_path, pgm=True)
dec.decode_all_frames()
process = subprocess.run(
[PSNR_TOOL_PATH, input_path, output_path, bitstream_path],
stdout=subprocess.PIPE,
)
stdout = process.stdout.decode("utf-8")
bpp, db = stdout.split(' bpp ')
bpp, db = float(bpp), float(db.replace(' dB', ''))
db = 0.0 if math.isinf(db) else db
df.loc[index] = [bpp, db]
version_path = os.path.join(DATA_ROOT_PATH, version)
print(version)
if not os.path.exists(version_path):
os.mkdir(version_path)
df.to_pickle(os.path.join(version_path, filename + DATA_SUFFIX))
def main():
parser = argparse.ArgumentParser(description='image/video encoder')
parser.add_argument('-bs', '--blocksize',
help='block size in samples (default: 16)',
default=16,
dest='blocksize',
type=int)
parser.add_argument('-qp', '--quantization-parameter',
help='quantization parameter, range [0;31] (default: 12)',
default=12,
choices=(range(0, 32)),
dest='qp',
type=int)
parser.add_argument('-i', '--input',
help='input image in pgm format or input video',
required=True,
dest='input', )
parser.add_argument('-b', '--bitstream',
help='bitstream file written by encoder',
required=True,
dest='bitstream')
parser.add_argument('-r', '--reconstruct',
help='path for reconstructed image/video at the encoder side',
dest='reconstruction_path')
parser.add_argument('-s', '--size',
help='Specify the video dimensions (WxH) when encoding a video file',
default=None,
dest='video_size',
type=str)
parser.add_argument('-n', '--n-frames',
help='Specify the number of frames to be encoded (video only)',
default=30,
dest='n_frames',
type=int)
parser.add_argument('-sr', '--search-range',
help='Specify search range S',
default=8,
dest='search_range',
type=int)
parser.add_argument('-f', '--fast',
help='Use logarithmic motion vector search',
dest='use_fast',
action='store_true')
args = parser.parse_args()
start_time = time.process_time() # benchmarking speed
enc = Encoder(args.input, args.bitstream, args.blocksize, args.qp, args.use_fast, args.reconstruction_path)
if args.video_size is None:
enc.encode_image()
else:
width, height = list(map(int, args.video_size.split('x'))) # Parse width and height and cast to int
enc.encode_video(width, height, args.n_frames, args.search_range)
encoding_time = time.process_time() - start_time
print(f'it took {encoding_time * 1000} ms to encode')
