Minor doc TF Lite doc changes
PiperOrigin-RevId: 292541517 Change-Id: Id9620cdfa6b6ee1132ff609d37b4364c9f1bae06
This commit is contained in:
Khanh LeViet
TensorFlower Gardener
parent
6b0350800f
commit
9a565656e2
@ -1,8 +1,8 @@
|
||||
# Converter command line reference
|
||||
|
||||
This page describes how to use the [TensorFlow Lite converter](index.md) using
|
||||
the command line tool. The preferred approach for conversion is using the
|
||||
[Python API](python_api.md).
|
||||
the command line tool. However, The[Python API](python_api.md) is recommended
|
||||
for the majority of cases.
|
||||
|
||||
Note: This only contains documentation on the command line tool in TensorFlow 2.
|
||||
Documentation on using the command line tool in TensorFlow 1 is available on
|
||||
@ -10,20 +10,26 @@ GitHub
|
||||
([reference](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/g3doc/r1/convert/cmdline_reference.md),
|
||||
[example](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/g3doc/r1/convert/cmdline_examples.md)).
|
||||
|
||||
[TOC]
|
||||
|
||||
## High-level overview
|
||||
|
||||
The TensorFlow Lite Converter has a command line tool `tflite_convert` which
|
||||
supports basic models. Use the `TFLiteConverter` [Python API](python_api.md) for
|
||||
any conversions involving quantization or any additional parameters (e.g.
|
||||
The TensorFlow Lite Converter has a command line tool named `tflite_convert`,
|
||||
which supports basic models. Use the [Python API](python_api.md) for any
|
||||
conversions involving optimizations, or any additional parameters (e.g.
|
||||
signatures in [SavedModels](https://www.tensorflow.org/guide/saved_model) or
|
||||
custom objects in
|
||||
[Keras models](https://www.tensorflow.org/guide/keras/overview)).
|
||||
|
||||
## Usage
|
||||
|
||||
The following flags specify the input and output files.
|
||||
The following example shows a SavedModel being converted:
|
||||
|
||||
```bash
|
||||
tflite_convert \
|
||||
--saved_model_dir=/tmp/mobilenet_saved_model \
|
||||
--output_file=/tmp/mobilenet.tflite
|
||||
```
|
||||
|
||||
The inputs and outputs are specified using the following commonly used flags:
|
||||
|
||||
* `--output_file`. Type: string. Specifies the full path of the output file.
|
||||
* `--saved_model_dir`. Type: string. Specifies the full path to the directory
|
||||
@ -31,30 +37,33 @@ The following flags specify the input and output files.
|
||||
* `--keras_model_file`. Type: string. Specifies the full path of the HDF5 file
|
||||
containing the `tf.keras` model generated in 1.X or 2.X.
|
||||
|
||||
The following is an example usage.
|
||||
To use all of the available flags, use the following command:
|
||||
|
||||
```
|
||||
tflite_convert \
|
||||
--saved_model_dir=/tmp/mobilenet_saved_model \
|
||||
--output_file=/tmp/mobilenet.tflite
|
||||
```bash
|
||||
tflite_convert --help
|
||||
```
|
||||
|
||||
In addition to the input and output flags, the converter contains the following
|
||||
flag.
|
||||
The following flag can be used for compatibility with the TensorFlow 1.X version
|
||||
of the converter CLI:
|
||||
|
||||
* `--enable_v1_converter`. Type: bool. Enables user to enable the 1.X command
|
||||
line flags instead of the 2.X flags. The 1.X command line flags are
|
||||
specified
|
||||
[here](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/g3doc/r1/convert/cmdline_reference.md).
|
||||
|
||||
## Additional instructions
|
||||
## Installing the converter CLI
|
||||
|
||||
### Building from source
|
||||
To obtain the latest version of the TensorFlow Lite converter CLI, we recommend
|
||||
installing the nightly build using
|
||||
[pip](https://www.tensorflow.org/install/pip):
|
||||
|
||||
In order to run the latest version of the TensorFlow Lite Converter either
|
||||
install the nightly build using [pip](https://www.tensorflow.org/install/pip) or
|
||||
```bash
|
||||
pip install tf-nightly
|
||||
```
|
||||
|
||||
Alternatively, you can
|
||||
[clone the TensorFlow repository](https://www.tensorflow.org/install/source) and
|
||||
use `bazel`. An example can be seen below.
|
||||
use `bazel` to run the command:
|
||||
|
||||
```
|
||||
bazel run //tensorflow/lite/python:tflite_convert -- \
|
||||
|
||||
@ -6,8 +6,9 @@ following example.
|
||||
<a class="button button-primary" href="https://github.com/tensorflow/examples/tree/master/lite/examples/image_classification/android">Android
|
||||
image classification example</a>
|
||||
|
||||
For an explanation of the source code, you should also read
|
||||
[TensorFlow Lite Android image classification](https://github.com/tensorflow/examples/blob/master/lite/examples/image_classification/android/EXPLORE_THE_CODE.md).
|
||||
Read
|
||||
[TensorFlow Lite Android image classification](https://github.com/tensorflow/examples/blob/master/lite/examples/image_classification/android/EXPLORE_THE_CODE.md)
|
||||
for an explanation of the source code.
|
||||
|
||||
This example app uses
|
||||
[image classification](https://www.tensorflow.org/lite/models/image_classification/overview)
|
||||
@ -100,11 +101,10 @@ or you may wish to make local changes to TensorFlow Lite.
|
||||
|
||||
#### Install Bazel and Android Prerequisites
|
||||
|
||||
Bazel is the primary build system for TensorFlow. To build with Bazel, it and
|
||||
the Android NDK and SDK must be installed on your system.
|
||||
Bazel is the primary build system for TensorFlow. To build with it, you must
|
||||
have it and the Android NDK and SDK installed on your system.
|
||||
|
||||
1. Install the latest version of Bazel as per the instructions
|
||||
[on the Bazel website](https://bazel.build/versions/master/docs/install.html).
|
||||
1. Install the latest version of the [Bazel build system](https://bazel.build/versions/master/docs/install.html).
|
||||
2. The Android NDK is required to build the native (C/C++) TensorFlow Lite
|
||||
code. The current recommended version is 17c, which may be found
|
||||
[here](https://developer.android.com/ndk/downloads/older_releases.html#ndk-17c-downloads).
|
||||
@ -176,3 +176,35 @@ dependencies {
|
||||
compile(name:'tensorflow-lite', ext:'aar')
|
||||
}
|
||||
```
|
||||
|
||||
##### Install AAR to local Maven repository
|
||||
|
||||
Execute the following command from your root checkout directory:
|
||||
|
||||
```sh
|
||||
mvn install:install-file \
|
||||
-Dfile=bazel-bin/tensorflow/lite/java/tensorflow-lite.aar \
|
||||
-DgroupId=org.tensorflow \
|
||||
-DartifactId=tensorflow-lite -Dversion=0.1.100 -Dpackaging=aar
|
||||
```
|
||||
|
||||
In your app's `build.gradle`, ensure you have the `mavenLocal()` dependency and
|
||||
replace the standard TensorFlow Lite dependency with the one that has support
|
||||
for select TensorFlow ops:
|
||||
|
||||
```
|
||||
allprojects {
|
||||
repositories {
|
||||
jcenter()
|
||||
mavenLocal()
|
||||
}
|
||||
}
|
||||
|
||||
dependencies {
|
||||
implementation 'org.tensorflow:tensorflow-lite-with-select-tf-ops:0.1.100'
|
||||
}
|
||||
```
|
||||
|
||||
Note that the `0.1.100` version here is purely for the sake of
|
||||
testing/development. With the local AAR installed, you can use the standard
|
||||
[TensorFlow Lite Java inference APIs](../guide/inference.md) in your app code.
|
||||
|
||||
@ -28,10 +28,9 @@ improve:
|
||||
TensorFlow Lite works with a huge range of devices, from tiny microcontrollers
|
||||
to powerful mobile phones.
|
||||
|
||||
Key Point: The TensorFlow Lite binary is smaller than 1MB when all supported
|
||||
operators are linked (for 32-bit ARM builds), and less than 300KB when using
|
||||
only the operators needed for supporting the common image classification models
|
||||
InceptionV3 and MobileNet.
|
||||
Key Point: The TensorFlow Lite binary is smaller than 300KB when all supported
|
||||
operators are linked, and less than 200KB when using only the operators needed
|
||||
for supporting the common image classification models InceptionV3 and MobileNet.
|
||||
|
||||
## Get started
|
||||
|
||||
|
||||
@ -26,8 +26,7 @@ TensorFlow Lite offers native iOS libraries written in
|
||||
[Swift](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/lite/experimental/swift)
|
||||
and
|
||||
[Objective-C](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/lite/experimental/objc).
|
||||
To get started quickly writing your own iOS code, we recommend using our
|
||||
[Swift image classification example](https://github.com/tensorflow/examples/tree/master/lite/examples/image_classification/ios)
|
||||
Start writing your own iOS code using the [Swift image classification example](https://github.com/tensorflow/examples/tree/master/lite/examples/image_classification/ios)
|
||||
as a starting point.
|
||||
|
||||
The sections below demonstrate how to add TensorFlow Lite Swift or Objective-C
|
||||
@ -57,16 +56,16 @@ There are stable releases, and nightly releases available for both
|
||||
version constraint as in the above examples, CocoaPods will pull the latest
|
||||
stable release by default.
|
||||
|
||||
You can also specify a version contraint. For example, if you wish to depend on
|
||||
You can also specify a version constraint. For example, if you wish to depend on
|
||||
version 2.0.0, you can write the dependency as:
|
||||
|
||||
```ruby
|
||||
pod 'TensorFlowLiteSwift', '~> 2.0.0'
|
||||
```
|
||||
|
||||
This will ensure the latest available 2.x.y version of `TensorFlowLiteSwift` pod
|
||||
is used in your app. Alternatively, if you want to depend on the nightly builds,
|
||||
you can write:
|
||||
This will ensure the latest available 2.x.y version of the `TensorFlowLiteSwift`
|
||||
pod is used in your app. Alternatively, if you want to depend on the nightly
|
||||
builds, you can write:
|
||||
|
||||
```ruby
|
||||
pod 'TensorFlowLiteSwift', '0.0.1-nightly'
|
||||
|
||||
@ -9,8 +9,8 @@ Since the set of TensorFlow Lite operations is smaller than TensorFlow's, not
|
||||
every model is convertible. Even for supported operations, very specific usage
|
||||
patterns are sometimes expected, for performance reasons. We expect to expand
|
||||
the set of supported operations in future TensorFlow Lite releases. Additional
|
||||
ops can be included by [using select TensorFlow ops](ops_select.md), at the cost
|
||||
of binary size.
|
||||
ops can be included by [using select TensorFlow ops](ops_select.md), at
|
||||
the cost of binary size.
|
||||
|
||||
The best way to understand how to build a TensorFlow model that can be used with
|
||||
TensorFlow Lite is to carefully consider how operations are converted and
|
||||
@ -18,9 +18,9 @@ optimized, along with the limitations imposed by this process.
|
||||
|
||||
## Supported types
|
||||
|
||||
Most TensorFlow Lite operations target both floating-point (float32) and
|
||||
quantized (uint8, int8) inference, but many ops do not yet for other types like
|
||||
tf.float16 and strings.
|
||||
Most TensorFlow Lite operations target both floating-point (`float32`) and
|
||||
quantized (`uint8`, `int8`) inference, but many ops do not yet for other types
|
||||
like `tf.float16` and strings.
|
||||
|
||||
Apart from using different version of the operations, the other difference
|
||||
between floating-point and quantized models lies in the way they are converted.
|
||||
@ -1141,8 +1141,8 @@ Outputs {
|
||||
}
|
||||
```
|
||||
|
||||
And these are TensorFlow Lite operations that are present but not ready for
|
||||
custom models yet:
|
||||
The following TensorFlow Lite operations are present, but not ready for custom
|
||||
models:
|
||||
|
||||
* `CALL`
|
||||
* `CONCAT_EMBEDDINGS`
|
||||
|
||||
@ -16,10 +16,11 @@ To quickly run TensorFlow Lite models with Python, you can install just the
|
||||
TensorFlow Lite interpreter, instead of all TensorFlow packages.
|
||||
|
||||
This interpreter-only package is a fraction the size of the full TensorFlow
|
||||
package and includes only the code required to run inferences, such as the
|
||||
package and includes the bare minimum code required to run inferences with
|
||||
TensorFlow Lite—it includes only the
|
||||
[`tf.lite.Interpreter`](https://www.tensorflow.org/api_docs/python/tf/lite/Interpreter)
|
||||
class. This small package is ideal when all you want to do is execute `.tflite`
|
||||
models.
|
||||
Python class. This small package is ideal when all you want to do is execute
|
||||
`.tflite` models and avoid wasting disk space with the large TensorFlow library.
|
||||
|
||||
Note: If you need access to other Python APIs, such as the [TensorFlow Lite
|
||||
Converter](../convert/python_api.md), you must install the [full TensorFlow
|
||||
|
||||
Loading…
Reference in New Issue
Block a user