Skip to content

[tensorrt] Failed Execution #3835

Closed
Closed
@Davidnet

Description

@Davidnet

System information

  • What is the top-level directory of the model you are using: models
  • Have I written custom code (as opposed to using a stock example script provided in TensorFlow): no
  • OS Platform and Distribution (e.g., Linux Ubuntu 16.04): xenial
  • TensorFlow installed from (source or binary): binary
  • TensorFlow version (use command below): 1.7.0
  • Bazel version (if compiling from source):
  • CUDA/cuDNN version: 9.0/7.1
  • GPU model and memory: k80 11gb
  • Exact command to reproduce:
    python tensorrt.py --frozen_graph=resnetv2_imagenet_frozen_graph.pb --image_file=image.jpg --native --fp32 --fp16 --output_dir=output

Describe the problem

fresh os installation, try to use the tensorrt example.

Source code / logs

totalMemory: 11.17GiB freeMemory: 11.10GiB
2018-04-02 10:05:26.213549: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1423] Adding visible gpu devices: 0
2018-04-02 10:05:26.603186: I tensorflow/core/common_runtime/gpu/gpu_device.cc:911] Device interconnect StreamExecutor with strength 1 edge matrix:
2018-04-02 10:05:26.603241: I tensorflow/core/common_runtime/gpu/gpu_device.cc:917]      0
2018-04-02 10:05:26.603258: I tensorflow/core/common_runtime/gpu/gpu_device.cc:930] 0:   N
2018-04-02 10:05:26.603571: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1041] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 5719 MB memory) -> physical GPU (device: 0, name: Tesla K80, pci bus id: 00
00:00:1e.0, compute capability: 3.7)
Running native graph
INFO:tensorflow:Starting execution
2018-04-02 10:05:27.325531: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1423] Adding visible gpu devices: 0
2018-04-02 10:05:27.325604: I tensorflow/core/common_runtime/gpu/gpu_device.cc:911] Device interconnect StreamExecutor with strength 1 edge matrix:
2018-04-02 10:05:27.325624: I tensorflow/core/common_runtime/gpu/gpu_device.cc:917]      0
2018-04-02 10:05:27.325636: I tensorflow/core/common_runtime/gpu/gpu_device.cc:930] 0:   N
2018-04-02 10:05:27.325831: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1041] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 5719 MB memory) -> physical GPU (device: 0, name: Tesla K80, pci bus id: 00
00:00:1e.0, compute capability: 3.7)
INFO:tensorflow:Starting Warmup cycle
2018-04-02 10:05:28.814376: E tensorflow/stream_executor/cuda/cuda_dnn.cc:396] Loaded runtime CuDNN library: 7102 (compatibility version 7100) but source was compiled with 7005 (compatibility version 7000).  If using a binary install, up
grade your CuDNN library to match.  If building from sources, make sure the library loaded at runtime matches a compatible version specified during compile configuration.
2018-04-02 10:05:28.815023: F tensorflow/core/kernels/conv_ops.cc:712] Check failed: stream->parent()->GetConvolveAlgorithms( conv_parameters.ShouldIncludeWinogradNonfusedAlgo<T>(), &algorithms)
Aborted (core dumped)

Metadata

Metadata

Assignees

Labels

No labels
No labels

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions