Question

我使用TensorRT进行Int8校准。

一旦校准完成并测试推断。我在以下功能的stream.synchronize()处出错。

在FP32和FP16引擎上运行没有问题。仅在Int8引擎上运行时出错。怎么了？

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.

Answer 1

以下代码没有错误。仅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]

错误：engine.cpp（370）-〜ExecutionContext中的Cuda错误：77

1 个答案: