def export_engine(model,
im,
file,
train,
half,
simplify,
workspace=4,
verbose=False,
prefix=colorstr('TensorRT:')):
try:
check_requirements(('tensorrt', ))
import tensorrt as trt
opset = (12,
13)[trt.__version__[0] == '8'] # test on TensorRT 7.x and 8.x
export_onnx(model, im, file, opset, train, False, simplify)
onnx = file.with_suffix('.onnx')
assert onnx.exists(), f'failed to export ONNX file: {onnx}'
LOGGER.info(
f'\n{prefix} starting export with TensorRT {trt.__version__}...')
f = file.with_suffix('.engine') # TensorRT engine file
logger = trt.Logger(trt.Logger.INFO)
if verbose:
logger.min_severity = trt.Logger.Severity.VERBOSE
builder = trt.Builder(logger)
config = builder.create_builder_config()
config.max_workspace_size = workspace * 1 << 30
flag = (1 << int(trt.NetworkDefinitionCreationFlag.EXPLICIT_BATCH))
network = builder.create_network(flag)
parser = trt.OnnxParser(network, logger)
if not parser.parse_from_file(str(onnx)):
raise RuntimeError(f'failed to load ONNX file: {onnx}')
inputs = [network.get_input(i) for i in range(network.num_inputs)]
outputs = [network.get_output(i) for i in range(network.num_outputs)]
LOGGER.info(f'{prefix} Network Description:')
for inp in inputs:
LOGGER.info(
f'{prefix}\tinput "{inp.name}" with shape {inp.shape} and dtype {inp.dtype}'
)
for out in outputs:
LOGGER.info(
f'{prefix}\toutput "{out.name}" with shape {out.shape} and dtype {out.dtype}'
)
half &= builder.platform_has_fast_fp16
LOGGER.info(f'{prefix} building FP{16 if half else 32} engine in {f}')
if half:
config.set_flag(trt.BuilderFlag.FP16)
with builder.build_engine(network, config) as engine, open(f,
'wb') as t:
t.write(engine.serialize())
LOGGER.info(
f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
except Exception as e:
LOGGER.info(f'\n{prefix} export failure: {e}')
def export_engine(model, im, file, train, half, simplify, workspace=4, verbose=False, prefix=colorstr('TensorRT:')):
# YOLOv5 TensorRT export https://developer.nvidia.com/tensorrt
try:
assert im.device.type != 'cpu', 'export running on CPU but must be on GPU, i.e. `python export.py --device 0`'
try:
import tensorrt as trt
except Exception:
if platform.system() == 'Linux':
check_requirements(('nvidia-tensorrt',), cmds=('-U --index-url https://pypi.ngc.nvidia.com',))
import tensorrt as trt
if trt.__version__[0] == '7': # TensorRT 7 handling https://github.com/ultralytics/yolov5/issues/6012
grid = model.model[-1].anchor_grid
model.model[-1].anchor_grid = [a[..., :1, :1, :] for a in grid]
export_onnx(model, im, file, 12, train, False, simplify) # opset 12
model.model[-1].anchor_grid = grid
else: # TensorRT >= 8
check_version(trt.__version__, '8.0.0', hard=True) # require tensorrt>=8.0.0
export_onnx(model, im, file, 13, train, False, simplify) # opset 13
onnx = file.with_suffix('.onnx')
LOGGER.info(f'\n{prefix} starting export with TensorRT {trt.__version__}...')
assert onnx.exists(), f'failed to export ONNX file: {onnx}'
f = file.with_suffix('.engine') # TensorRT engine file
logger = trt.Logger(trt.Logger.INFO)
if verbose:
logger.min_severity = trt.Logger.Severity.VERBOSE
builder = trt.Builder(logger)
config = builder.create_builder_config()
config.max_workspace_size = workspace * 1 << 30
# config.set_memory_pool_limit(trt.MemoryPoolType.WORKSPACE, workspace << 30) # fix TRT 8.4 deprecation notice
flag = (1 << int(trt.NetworkDefinitionCreationFlag.EXPLICIT_BATCH))
network = builder.create_network(flag)
parser = trt.OnnxParser(network, logger)
if not parser.parse_from_file(str(onnx)):
raise RuntimeError(f'failed to load ONNX file: {onnx}')
inputs = [network.get_input(i) for i in range(network.num_inputs)]
outputs = [network.get_output(i) for i in range(network.num_outputs)]
LOGGER.info(f'{prefix} Network Description:')
for inp in inputs:
LOGGER.info(f'{prefix}\tinput "{inp.name}" with shape {inp.shape} and dtype {inp.dtype}')
for out in outputs:
LOGGER.info(f'{prefix}\toutput "{out.name}" with shape {out.shape} and dtype {out.dtype}')
LOGGER.info(f'{prefix} building FP{16 if builder.platform_has_fast_fp16 and half else 32} engine in {f}')
if builder.platform_has_fast_fp16 and half:
config.set_flag(trt.BuilderFlag.FP16)
with builder.build_engine(network, config) as engine, open(f, 'wb') as t:
t.write(engine.serialize())
LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
return f
except Exception as e:
LOGGER.info(f'\n{prefix} export failure: {e}')
