TensorRT6.0.1: ERROR: builtin_op_importers.cpp:695 In function importBatchNormalization:

[00/13/2020-21:46:09] [E] [TRT] (Unnamed Layer* 0) [Convolution]: at least 4 dimensions are required for input
While parsing node number 1 [BatchNormalization]:
ERROR: builtin_op_importers.cpp:695 In function importBatchNormalization:
[6] Assertion failed: scale_weights.shape == weights_shape
[00/13/2020-21:46:09] [E] Failed to parse onnx file
[00/13/2020-21:46:09] [E] Parsing model failed
[00/13/2020-21:46:09] [E] Engine could not be created

看网上给的方案比较麻烦：https://github.com/NVIDIA/TensorRT/issues/330

我这里的解决方案如下：

第一步：更换createNetworkV2(1U)为createNetwork()

完成第一步编译运行，如果还是没有结果，执行第二步：

第二步：更换exeContexts[contextIndex]->enqueueV2(cur.data...)....为exeContexts[contextIndex]->enqueue(1, cur.data(), streams[contextIndex]->get(), nullptr);

完成第二步应该就可以正常运行了，如果还有错，更改cmake中的算力，与你使用的GPU相匹配。