ResizeBilinear

In “https://docs.nvidia.com/deeplearning/sdk/tensorrt-archived/tensorrt-601/tensorrt-support-matrix/index.html”, the ResizeBilinear op is said to support, but Warning: No conversion function registered for layer: ResizeBilinear yet. !!!

Hi,

Can you provide the following information so we can better help?

Provide details on the platforms you are using:
Linux distro and version
GPU type
Nvidia driver version
CUDA version
CUDNN version
Python version [if using python]
Tensorflow version
TensorRT version
If Jetson, OS, hw versions

Files

Include any logs, source, models (.uff, .pb, etc.) that would be helpful to diagnose the problem.

If relevant, please include the full traceback.


Reproducibility

Please provide a minimal test case that reproduces your error.

Ubuntu16.04
P40
396.26
9.0
7.6.3
3.6.8
1.12
6.0.1.5

# Author: Jiarenyf ...

import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'

import warnings
warnings.filterwarnings(action='ignore', category=FutureWarning)

#---------------------------------------------------------------------

import tensorflow as tf

######################################################################

if __name__ == '__main__':
    with tf.Graph().as_default() as graph:
        t = tf.placeholder(tf.float32, shape=(1,160,160,64), name='input')
        t = tf.image.resize_bilinear(t, (320, 320), name="output")
        tf.io.write_graph(graph, '.', '/dev/shm/error.pb', as_text=False)
        os.system('convert-to-uff /dev/shm/error.pb')

@NVES_R

Hi,

So it seems that the current support matrix docs are a little misleading. The UFF parser does not support the ResizeBilinear op.

You can either try to use TF-TRT (Accelerating Inference In TF-TRT User Guide :: NVIDIA Deep Learning Frameworks Documentation), or TF-ONNX+ONNX Parser (GitHub - onnx/tensorflow-onnx: Convert TensorFlow, Keras, Tensorflow.js and Tflite models to ONNX) instead of the UFF Parser for converting your model to TensorRT.

For future reference, here are the supported UFF ops: UFF Operators — NVIDIA TensorRT Standard Python API Documentation 8.4.3 documentation

Thanks,
NVIDIA Enterprise Support

When would the uff-convertor update to support the ResizeBilinear op ?
Could you please give me a deadline ?

There are no current plans to add more features to the UFF parser. The ONNX parser is more actively being updated.

Because of this, tf2onnx (GitHub - onnx/tensorflow-onnx: Convert TensorFlow, Keras, Tensorflow.js and Tflite models to ONNX) is currently the path forward for TensorRT deployment from Tensorflow models, but TF-TRT (Accelerating Inference In TF-TRT User Guide :: NVIDIA Deep Learning Frameworks Documentation) is also supported in case TF->ONNX conversion fails.