python实现tensorrt推理

trt推理

python实现tensoort的推理，需要先将onnx转成tensorrt模型。转换的方法在上一篇博客中onnx2trt

class HostDeviceMem(object):
    def __init__(self, host_mem, device_mem):
        self.host = host_mem
        self.device = device_mem
    def __str__(self):
        return "Host:\n" + str(self.host) + "\nDevice:\n" + str(self.device)
    def __repr__(self):
        return self.__str__()
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 ti 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
def do_inference(context, bindings, inputs, outputs, stream, batch_size=1):
    # Transfer input 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_dtod_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]


with open('./ckpt/0903_t3_seg.trt', 'rb') as f, trt.Runtime(trt.Logger()) as runtime:
        engine = runtime.deserialize_cuda_engine(f.read())
context = engine.create_execution_context()
inputs, outputs, bindings, stream = allocate_buffers(engine)
inputs[0].host = np.random(1,3,1152,1152)
output_shape = (1,8,144,144)
trt_outs = do_inference(context, bindings, inputs, outputs, stream)
# trt_outs = 
print(trt_outs, trt_outs.shape)