diff options
Diffstat (limited to 'tensorflow/contrib/tensorrt/README.md')
| -rw-r--r-- | tensorflow/contrib/tensorrt/README.md | 23 |
1 files changed, 4 insertions, 19 deletions
diff --git a/tensorflow/contrib/tensorrt/README.md b/tensorflow/contrib/tensorrt/README.md index dfcce0fd00..461e627e99 100644 --- a/tensorflow/contrib/tensorrt/README.md +++ b/tensorflow/contrib/tensorrt/README.md @@ -2,7 +2,8 @@ Using TensorRT in TensorFlow ============================ This module provides necessary bindings and introduces TRT_engine_op -operator that wraps a subgraph in TensorRT. +operator that wraps a subgraph in TensorRT. This is still a work in progress +but should be useable with most common graphs. Compilation ----------- @@ -15,26 +16,10 @@ configure script should find the necessary components from the system automatically. If installed from tar packages, user has to set path to location where the library is installed during configuration. - -``` +```shell bazel build --config=cuda --config=opt //tensorflow/tools/pip_package:build_pip_package bazel-bin/tensorflow/tools/pip_package/build_pip_package /tmp/ ``` After the installation of tensorflow package, TensorRT transformation -will be available. An example use is shown below. - -```python -import tensorflow as tf -import tensorflow.contrib.tensorrt as trt -#... create and train or load model -gdef = sess.graph.as_graph_def() -trt_gdef = trt.create_inference_graph( - gdef, #original graph_def - ["output"], #name of output node(s) - max_batch_size, #maximum batch size to run the inference - max_workspace_size_bytes) # max memory for TensorRT to use -tf.reset_default_graph() -tf.import_graph_def(graph_def=trt_gdef) -#...... run inference -``` +will be available. An example use can be found in test/test_tftrt.py directory |