Warning: No conversion function registered for layer: ArgMax yet.

UFF Version 0.5.5
=== Automatically deduced input nodes ===
[name: “input”
op: “Placeholder”
attr {
key: “dtype”
value {
type: DT_FLOAT
}
}
attr {
key: “shape”
value {
shape {
dim {
size: -1
}
dim {
size: 224
}
dim {
size: 224
}
dim {
size: 3
}
}
}
}
]

Using output node output
Converting to UFF graph
Warning: No conversion function registered for layer: ArgMax yet.
Converting output as custom op: ArgMax
Warning: No conversion function registered for layer: AddV2 yet.
Converting fc8/add as custom op: AddV2
Warning: No conversion function registered for layer: AddV2 yet.
Converting fc7/add as custom op: AddV2
Warning: No conversion function registered for layer: AddV2 yet.
Converting fc6/add as custom op: AddV2
Warning: No conversion function registered for layer: AddV2 yet.
Converting conv5_3/add as custom op: AddV2
Warning: No conversion function registered for layer: AddV2 yet.
Converting conv5_2/add as custom op: AddV2
Warning: No conversion function registered for layer: AddV2 yet.
Converting conv5_1/add as custom op: AddV2
Warning: No conversion function registered for layer: AddV2 yet.
Converting conv4_3/add as custom op: AddV2
Warning: No conversion function registered for layer: AddV2 yet.
Converting conv4_2/add as custom op: AddV2
Warning: No conversion function registered for layer: AddV2 yet.
Converting conv4_1/add as custom op: AddV2
Warning: No conversion function registered for layer: AddV2 yet.
Converting conv3_3/add as custom op: AddV2
Warning: No conversion function registered for layer: AddV2 yet.
Converting conv3_2/add as custom op: AddV2
Warning: No conversion function registered for layer: AddV2 yet.
Converting conv3_1/add as custom op: AddV2
Warning: No conversion function registered for layer: AddV2 yet.
Converting conv2_2/add as custom op: AddV2
Warning: No conversion function registered for layer: AddV2 yet.
Converting conv2_1/add as custom op: AddV2
Warning: No conversion function registered for layer: AddV2 yet.
Converting conv1_2/add as custom op: AddV2
Warning: No conversion function registered for layer: AddV2 yet.
Converting conv1_1/add as custom op: AddV2
No. nodes: 92

how to solve this Warning?

Hi,
Please share more detail about how you hit the warning. Do you try to convert a TensorFlow to TensorRT? What is the model you would like to convert?

yes iam try TensorFlow to TensorRT
i am try this https://github.com/ppplinday/tensorflow-vgg16-train-and-test
get a pb model then i try to transform to uff model i want to run at tx2

import tensorflow as tf

import uff

需要改成你自己的output_names

output_names = [‘output’]
frozen_graph_filename = ‘vggs.pb’
uff_model = uff.from_tensorflow_frozen_model(frozen_graph_filename, output_names)
dump = open(‘VGG16.uff’, ‘wb’)
dump.write(uff_model)
dump.close()

Hi,
Looks like the layers are not supported. Please check the following links and see if you can ONNX to successfully convert the model.
https://devtalk.nvidia.com/default/topic/1069711/jetson-nano/get-an-error-when-convert-frozen-graph-to-tensorrt-engine/post/5418920/#5418920
https://devtalk.nvidia.com/default/topic/1066445/tensorrt/tensorrt-6-0-1-tensorflow-1-14-no-conversion-function-registered-for-layer-fusedbatchnormv3-yet/post/5403567/#5403567