Environment
TensorRT Version: 7.0
GPU Type: TX2
Nvidia Driver Version:
CUDA Version: 10.2
CUDNN Version:
Operating System + Version: ubuntu 18.04
Python Version (if applicable): 3.6
TensorFlow Version (if applicable): 1.15
PyTorch Version (if applicable):
Baremetal or Container (if container which image + tag):
Description
When I try to convert the ssdlite_mobilenetv2 model to tensorrt engine, it can convert to uff, but uff can’t convert to engine.
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:tensorflow:From /usr/lib/python3.6/dist-packages/uff/converters/tensorflow/converter.py:179: The name tf.AttrValue is deprecated. Please use tf.compat.v1.AttrValue instead.
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: FlattenConcat_TRT yet.
Converting concat_box_loc as custom op: FlattenConcat_TRT
DEBUG [/usr/lib/python3.6/dist-packages/uff/converters/tensorflow/converter.py:96] Marking ['NMS'] as outputs
No. nodes: 589
UFF Output written to tmp.uff
#assertionnmsPlugin.cpp,82
Aborted (core dumped)
But I can convert successfully on ssd_mobilenetv2, I found the difference between ssdlite_mobilnetv2 and ssd_mobilenetv2, there is no “Concatenate” operation in the ssdlite_mobilenetv2 model. So the PriorBox OP’s output can’t connect to the NMS OP’s input, which leads the assertionnmsPlugin error. But I don’t know how to modify the config.py below. someone can help? thanks!
import graphsurgeon as gs
path = 'model/ssd_mobilenet_v2_coco_2018_03_29/frozen_inference_graph.pb'
TRTbin = 'TRT_ssd_mobilenet_v2_coco_2018_03_29.bin'
output_name = ['NMS']
dims = [3,300,300]
layout = 7
def add_plugin(graph):
all_assert_nodes = graph.find_nodes_by_op("Assert")
graph.remove(all_assert_nodes, remove_exclusive_dependencies=True)
all_identity_nodes = graph.find_nodes_by_op("Identity")
graph.forward_inputs(all_identity_nodes)
Input = gs.create_plugin_node(
name="Input",
op="Placeholder",
shape=[1, 3, 300, 300]
)
PriorBox = gs.create_plugin_node(
name="GridAnchor",
op="GridAnchor_TRT",
minSize=0.2,
maxSize=0.95,
aspectRatios=[1.0, 2.0, 0.5, 3.0, 0.33],
variance=[0.1,0.1,0.2,0.2],
featureMapShapes=[19, 10, 5, 3, 2, 1],
numLayers=6
)
NMS = gs.create_plugin_node(
name="NMS",
op="NMS_TRT",
shareLocation=1,
varianceEncodedInTarget=0,
backgroundLabelId=0,
confidenceThreshold=1e-8,
nmsThreshold=0.6,
topK=100,
keepTopK=100,
numClasses=91,
inputOrder=[1, 0, 2],
confSigmoid=1,
isNormalized=1
)
concat_priorbox = gs.create_node(
"concat_priorbox",
op="ConcatV2",
axis=2
)
concat_box_loc = gs.create_plugin_node(
"concat_box_loc",
op="FlattenConcat_TRT",
)
concat_box_conf = gs.create_plugin_node(
"concat_box_conf",
op="FlattenConcat_TRT",
)
namespace_plugin_map = {
"MultipleGridAnchorGenerator": PriorBox,
"Postprocessor": NMS,
"Preprocessor": Input,
"ToFloat": Input,
"image_tensor": Input,
"Concatenate": concat_priorbox,
"concat": concat_box_loc,
"concat_1": concat_box_conf
}
graph.collapse_namespaces(namespace_plugin_map)
graph.remove(graph.graph_outputs, remove_exclusive_dependencies=False)
graph.find_nodes_by_op("NMS_TRT")[0].input.remove("Input")
return graph
