Error about tensorrt in jetson tx2

Autonomous Machines Jetson & Embedded 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

I fix this error. Then, this error occured.

Using output node NMS
Converting to UFF graph
Warning: No conversion function registered for layer: NMS_TRT yet.
Converting NMS as custom op: NMS_TRT
Warning: No conversion function registered for layer: FlattenConcat_TRT yet.
Converting concat_box_conf as custom op: FlattenConcat_TRT
Warning: No conversion function registered for layer: Cast yet.
Converting Cast as custom op: Cast
Warning: No conversion function registered for layer: GridAnchor_TRT yet.
Converting GridAnchor as custom op: GridAnchor_TRT
Warning: No conversion function registered for layer: FlattenConcat_TRT yet.
Converting concat_box_loc as custom op: FlattenConcat_TRT
No. nodes: 676
UFF Output written to tmp.uff
[TensorRT] ERROR: UFFParser: Validator error: Cast: Unsupported operation _Cast
[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. But, I run the script using my retrained data, errors continue to occur

3

Hi,

Please update the config.py with this mapping function to support CAST.

https://github.com/AastaNV/TRT_object_detection/blob/master/config/model_ssd_mobilenet_v2_coco_2018_03_29.py#L65

@@ -81,7 +81,7 @@ namespace_plugin_map = {
     "MultipleGridAnchorGenerator": PriorBox,
     "Postprocessor": NMS,
     "Preprocessor": Input,
-    "ToFloat": Input,
+    "Cast": Input,
     "image_tensor": Input,
     "Concatenate": concat_priorbox,
     "concat": concat_box_loc,
     "concat_1": concat_box_conf

Thanks.