tensorRT多batch动态推理

tensorRT的多batch推理，导出的onnx模型必须是动态batch，只需在导出的时候，设置一个dynamic_axis参数即可。

torch.onnx.export(hybrik_model, dummy_input,  "./best_model.onnx", verbose=True, input_names=input_names, \
                  output_names=output_names, opset_version=9, dynamic_axes={'input':{0:'batch'}, 'output':{0:'batch'}})

序列化的时候，要构建一个profile, 指定最小的、合适的以及最大的输入数据维度，增加如下代码：

IOptimizationProfile* profile = builder->createOptimizationProfile();
profile->setDimensions("input", OptProfileSelector::kMIN, Dims4(1, 3, 256, 256));
profile->setDimensions("input", OptProfileSelector::kOPT, Dims4(5, 3, 256, 256));
profile->setDimensions("input", OptProfileSelector::kMAX, Dims4(5, 3, 256, 256));
config->addOptimizationProfile(profile);

生成trt引擎的时候，可以打印维度，看batch维度是否为-1：

nvinfer1::Dims dim = engine->getBindingDimensions(0);
print_dims(dim);
void print_dims(const nvinfer1::Dims& dim)
{
    for (int nIdxShape = 0; nIdxShape < dim.nbDims; ++nIdxShape)
    {
        
        printf("dim %d=%d\n", nIdxShape, dim.d[nIdxShape]);
        
    }
}

在反序列化推理时，也需增加运行时维度的指定：
增加这一句：context->setBindingDimensions(0, Dims4(5, 3, 256, 256));

context->setBindingDimensions(0, Dims4(5, 3, 256, 256));
context->enqueueV2(gpu_buffers, stream, nullptr);

CUDA_CHECK(cudaMemcpyAsync(output_uvd, gpu_buffers[output_uvd_index], 
                           5 * 29 * 3 * sizeof(float), cudaMemcpyDeviceToHost, stream));
CUDA_CHECK(cudaMemcpyAsync(output_phi, gpu_buffers[output_phi_index], 
                           5 * 23 * 2 * sizeof(float), cudaMemcpyDeviceToHost, stream));
CUDA_CHECK(cudaMemcpyAsync(output_shape, gpu_buffers[output_shape_index], 
                           5 * 10 * sizeof(float), cudaMemcpyDeviceToHost, stream));                      
CUDA_CHECK(cudaMemcpyAsync(output_cam_depth, gpu_buffers[output_cam_depth_index], 
                           5 * 1 * 1 * sizeof(float), cudaMemcpyDeviceToHost, stream));
cudaStreamSynchronize(stream);

详见：https://blog.csdn.net/dou3516/article/details/125976923