About TRT-object-detecction

Robotics & Edge Computing Jetson Systems Jetson TX2
1

[TensorRT] ERROR: UFFParser: Validator error: FeatureExtractor/MobilenetV2/layer_19_2_Conv2d_5_3x3_s2_128_depthwise/BatchNorm/FusedBatchNormV3: Unsupported operation _FusedBatchNormV3
[TensorRT] ERROR: Network must have at least one output
Traceback (most recent call last):
File “main.py”, line 43, in
buf = engine.serialize()
AttributeError: ‘NoneType’ object has no attribute ‘serialize’

There was no error when the TRT-object-detection script was executed as it was.
So, I updated coco.py(add the item ‘face’ and delete the rest) and added my retrained new model to the model directory. (checkpoint, frozen_inference_graph.pb, model.ckpt-20000.data-00000-of 00001, model.ckpt-20000.index, model.ckpt-20000.meta, pipeline.config )

That will produce such an error.
Both the example and my model are ssd_mobilenet_v2_coco_2018_03_29 and my model is retrained with that model.
Tell me exactly what should be fixed in the TRT-object-detection example.
Or tell me how to detect through the TRT process.

I use JetsonTX2 and jetpack 4.2, tensorflow=1.14.0, tensorrt5.0

3

Hi,

This error indicates there is an unsupported layer in your model:

[TensorRT] ERROR: UFFParser: Validator error: FeatureExtractor/MobilenetV2/layer_19_2_Conv2d_5_3x3_s2_128_depthwise/BatchNorm/FusedBatchNormV3: Unsupported operation _FusedBatchNormV3

FusedBatchNormV3 is operation in newer TensorFlow version.
To fix this, please switch the operation into the supported FusedBatchNorm instead.

https://github.com/AastaNV/TRT_object_detection/blob/master/config/model_ssd_mobilenet_v2_coco_2018_03_29.py#L78

...
graph.find_nodes_by_op("NMS_TRT")[0].input.remove("Input")

fusedbatchnorm_nodes = graph.find_nodes_by_op("FusedBatchNormV3")
for node in fusedbatchnorm_nodes:
        node.op = "FusedBatchNorm"

return graph

Thanks.