如何使用python api进行批量输入的TensorRT 7.0推理？

import tensorrt as trt
import pycuda.driver as cuda
import pycuda.autoinit
import numpy as np

# 加载TensorRT引擎
def load_engine(engine_path):
    with open(engine_path, 'rb') as f:
        engine_data = f.read()
    runtime = trt.Runtime(trt.Logger(trt.Logger.WARNING))
    engine = runtime.deserialize_cuda_engine(engine_data)
    return engine

# 创建输入和输出缓冲区
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))
        host_mem = cuda.pagelocked_empty(size, dtype)
        device_mem = cuda.mem_alloc(host_mem.nbytes)
        bindings.append(int(device_mem))
        if engine.binding_is_input(binding):
            inputs.append({'host': host_mem, 'device': device_mem})
        else:
            outputs.append({'host': host_mem, 'device': device_mem})
    return inputs, outputs, bindings, stream

# 执行推理
def do_inference(engine, inputs, outputs, bindings, stream):
    with engine.create_execution_context() as context:
        for inp in inputs:
            cuda.memcpy_htod_async(inp['device'], inp['host'], stream)
        context.execute_async_v2(bindings=bindings, stream_handle=stream.handle)
        for out in outputs:
            cuda.memcpy_dtoh_async(out['host'], out['device'], stream)
        stream.synchronize()

# 加载TensorRT引擎
engine = load_engine('path/to/your/engine.trt')

# 创建输入和输出缓冲区
inputs, outputs, bindings, stream = allocate_buffers(engine)

# 准备输入数据
input_data = np.random.randn(engine.max_batch_size, input_shape).astype(np.float32)

# 将输入数据复制到输入缓冲区
inputs[0]['host'] = input_data

# 执行推理
do_inference(engine, inputs, outputs, bindings, stream)

# 处理推理结果
output_data = outputs[0]['host']