ERROR: engine.cpp (370) - Cuda Error in ~ExecutionContext: 77
ERROR: engine.cpp (370) - Cuda Error in ~ExecutionContext: 77
我使用 TensorRT 进行 Int8 校准。
校准完成后测试推理。我在以下函数的 stream.synchronize()
处出错。
在 FP32 和 FP16 引擎上没有问题 运行。只有 Int8 引擎有错误 运行。有什么问题吗?
def infer(engine, x, batch_size, context):
inputs = []
outputs = []
bindings = []
stream = cuda.Stream()
for binding in engine:
size = trt.volume(engine.get_binding_shape(binding)) * batch_size
dtype = trt.nptype(engine.get_binding_dtype(binding))
# Allocate host and device buffers
host_mem = cuda.pagelocked_empty(size, dtype)
device_mem = cuda.mem_alloc(host_mem.nbytes)
# Append the device buffer to device bindings.
bindings.append(int(device_mem))
# Append to the appropriate list.
if engine.binding_is_input(binding):
inputs.append(HostDeviceMem(host_mem, device_mem))
else:
outputs.append(HostDeviceMem(host_mem, device_mem))
#img = np.array(x).ravel()
im = np.array(x, dtype=np.float32, order='C')
im = im[:,:,::-1]
#im = im.transpose((2,0,1))
#np.copyto(inputs[0].host, x.flatten()) #1.0 - img / 255.0
np.copyto(inputs[0].host, im.flatten())
[cuda.memcpy_htod_async(inp.device, inp.host, stream) for inp in inputs]
context.execute_async(batch_size=batch_size, bindings=bindings, stream_handle=stream.handle)
# Transfer predictions back from the GPU.
[cuda.memcpy_dtoh_async(out.host, out.device, stream) for out in outputs]
# Synchronize the stream
stream.synchronize()
# Return only the host outputs.
以下代码没有错误。只有 engine.max_batch_size 和 batch_size 不同。
def allocate_buffers(engine):
inputs = []
outputs = []
bindings = []
stream = cuda.Stream()
for binding in engine:
size = trt.volume(engine.get_binding_shape(binding)) * engine.max_batch_size
dtype = trt.nptype(engine.get_binding_dtype(binding))
# Allocate host and device buffers
host_mem = cuda.pagelocked_empty(size, dtype)
device_mem = cuda.mem_alloc(host_mem.nbytes)
# Append the device buffer to device bindings.
bindings.append(int(device_mem))
# Append to the appropriate list.
if engine.binding_is_input(binding):
inputs.append(HostDeviceMem(host_mem, device_mem))
else:
outputs.append(HostDeviceMem(host_mem, device_mem))
return inputs, outputs, bindings, stream
# This function is generalized for multiple inputs/outputs.
# inputs and outputs are expected to be lists of HostDeviceMem objects.
def do_inference(context, bindings, inputs, outputs, stream, batch_size=1):
# Transfer input data to the GPU.
[cuda.memcpy_htod_async(inp.device, inp.host, stream) for inp in inputs]
# Run inference.
context.execute_async(batch_size=batch_size, bindings=bindings, stream_handle=stream.handle)
# Transfer predictions back from the GPU.
[cuda.memcpy_dtoh_async(out.host, out.device, stream) for out in outputs]
# Synchronize the stream
stream.synchronize()
# Return only the host outputs.
return [out.host for out in outputs]
我使用 TensorRT 进行 Int8 校准。
校准完成后测试推理。我在以下函数的 stream.synchronize()
处出错。
在 FP32 和 FP16 引擎上没有问题 运行。只有 Int8 引擎有错误 运行。有什么问题吗?
def infer(engine, x, batch_size, context):
inputs = []
outputs = []
bindings = []
stream = cuda.Stream()
for binding in engine:
size = trt.volume(engine.get_binding_shape(binding)) * batch_size
dtype = trt.nptype(engine.get_binding_dtype(binding))
# Allocate host and device buffers
host_mem = cuda.pagelocked_empty(size, dtype)
device_mem = cuda.mem_alloc(host_mem.nbytes)
# Append the device buffer to device bindings.
bindings.append(int(device_mem))
# Append to the appropriate list.
if engine.binding_is_input(binding):
inputs.append(HostDeviceMem(host_mem, device_mem))
else:
outputs.append(HostDeviceMem(host_mem, device_mem))
#img = np.array(x).ravel()
im = np.array(x, dtype=np.float32, order='C')
im = im[:,:,::-1]
#im = im.transpose((2,0,1))
#np.copyto(inputs[0].host, x.flatten()) #1.0 - img / 255.0
np.copyto(inputs[0].host, im.flatten())
[cuda.memcpy_htod_async(inp.device, inp.host, stream) for inp in inputs]
context.execute_async(batch_size=batch_size, bindings=bindings, stream_handle=stream.handle)
# Transfer predictions back from the GPU.
[cuda.memcpy_dtoh_async(out.host, out.device, stream) for out in outputs]
# Synchronize the stream
stream.synchronize()
# Return only the host outputs.
以下代码没有错误。只有 engine.max_batch_size 和 batch_size 不同。
def allocate_buffers(engine):
inputs = []
outputs = []
bindings = []
stream = cuda.Stream()
for binding in engine:
size = trt.volume(engine.get_binding_shape(binding)) * engine.max_batch_size
dtype = trt.nptype(engine.get_binding_dtype(binding))
# Allocate host and device buffers
host_mem = cuda.pagelocked_empty(size, dtype)
device_mem = cuda.mem_alloc(host_mem.nbytes)
# Append the device buffer to device bindings.
bindings.append(int(device_mem))
# Append to the appropriate list.
if engine.binding_is_input(binding):
inputs.append(HostDeviceMem(host_mem, device_mem))
else:
outputs.append(HostDeviceMem(host_mem, device_mem))
return inputs, outputs, bindings, stream
# This function is generalized for multiple inputs/outputs.
# inputs and outputs are expected to be lists of HostDeviceMem objects.
def do_inference(context, bindings, inputs, outputs, stream, batch_size=1):
# Transfer input data to the GPU.
[cuda.memcpy_htod_async(inp.device, inp.host, stream) for inp in inputs]
# Run inference.
context.execute_async(batch_size=batch_size, bindings=bindings, stream_handle=stream.handle)
# Transfer predictions back from the GPU.
[cuda.memcpy_dtoh_async(out.host, out.device, stream) for out in outputs]
# Synchronize the stream
stream.synchronize()
# Return only the host outputs.
return [out.host for out in outputs]