experiments/STT-tensorflow
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Fix broken links and spelling errors

Browse Source 
PiperOrigin-RevId: 236786449
This commit is contained in:
A. Unique TensorFlower 2019-03-04 22:18:43 -08:00 committed by TensorFlower Gardener
parent 98c4548b4b
commit b71b8ecf64
15 changed files with 77 additions and 77 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
tensorflow/lite/g3doc/convert/cmdline_examples.md
View File

@ -64,19 +64,19 @@ tflite_convert \
--saved_model_dir=/tmp/saved_model --saved_model_dir=/tmp/saved_model
``` ```
[SavedModel](https://www.tensorflow.org/guide/saved_model#using_savedmodel_with_estimators) [SavedModel](https://www.tensorflow.org/guide/saved_model.md#using_savedmodel_with_estimators)
has fewer required flags than frozen graphs due to access to additional data has fewer required flags than frozen graphs due to access to additional data
contained within the SavedModel. The values for `--input_arrays` and contained within the SavedModel. The values for `--input_arrays` and
`--output_arrays` are an aggregated, alphabetized list of the inputs and outputs `--output_arrays` are an aggregated, alphabetized list of the inputs and outputs
in the [SignatureDefs](https://www.tensorflow.org/serving/signature_defs) within in the [SignatureDefs](../../serving/signature_defs.md) within
the the
[MetaGraphDef](https://www.tensorflow.org/guide/saved_model#apis_to_build_and_load_a_savedmodel) [MetaGraphDef](https://www.tensorflow.org/saved_model.md#apis_to_build_and_load_a_savedmodel)
specified by `--saved_model_tag_set`. As with the GraphDef, the value for specified by `--saved_model_tag_set`. As with the GraphDef, the value for
`input_shapes` is automatically determined whenever possible. `input_shapes` is automatically determined whenever possible.
There is currently no support for MetaGraphDefs without a SignatureDef or for There is currently no support for MetaGraphDefs without a SignatureDef or for
MetaGraphDefs that use the [`assets/` MetaGraphDefs that use the [`assets/`
directory](https://www.tensorflow.org/guide/saved_model#structure_of_a_savedmodel_directory). directory](https://www.tensorflow.org/guide/saved_model.md#structure_of_a_savedmodel_directory).
### Convert a tf.Keras model <a name="keras"></a> ### Convert a tf.Keras model <a name="keras"></a>

2
tensorflow/lite/g3doc/convert/cmdline_reference.md
View File

@ -38,7 +38,7 @@ The following flags specify optional parameters when using SavedModels.
Specifies a comma-separated set of tags identifying the MetaGraphDef within Specifies a comma-separated set of tags identifying the MetaGraphDef within
the SavedModel to analyze. All tags in the tag set must be specified. the SavedModel to analyze. All tags in the tag set must be specified.
* `--saved_model_signature_key`. Type: string. Default: * `--saved_model_signature_key`. Type: string. Default:
[DEFAULT_SERVING_SIGNATURE_DEF_KEY](https://www.tensorflow.org/api_docs/python/tf/saved_model/signature_constants). `tf.saved_model.signature_constants.DEFAULT_SERVING_SIGNATURE_DEF_KEY`.
Specifies the key identifying the SignatureDef containing inputs and Specifies the key identifying the SignatureDef containing inputs and
outputs. outputs.

4
tensorflow/lite/g3doc/convert/python_api.md
View File

@ -241,8 +241,8 @@ interpreter.allocate_tensors()
In order to run the latest version of the TensorFlow Lite Converter Python API, In order to run the latest version of the TensorFlow Lite Converter Python API,
either install the nightly build with either install the nightly build with
[pip](https://www.tensorflow.org/install/pip) (recommended) or [pip](https://www.tensorflow.org/install/pip) (recommended) or
[Docker](https://www.tensorflow.org/install/docker), or [Docker](https://www.tensorflow.org/install/docker.md), or
[build the pip package from source](https://www.tensorflow.org/install/source). [build the pip package from source](https://www.tensorflow.org/install/source.md).
### Converting models from TensorFlow 1.12 <a name="pre_tensorflow_1.12"></a> ### Converting models from TensorFlow 1.12 <a name="pre_tensorflow_1.12"></a>

2
tensorflow/lite/g3doc/guide/build_ios.md
View File

@ -3,7 +3,7 @@
This document describes how to build TensorFlow Lite iOS library. If you just This document describes how to build TensorFlow Lite iOS library. If you just
want to use it, the easiest way is using the TensorFlow Lite CocoaPod releases. want to use it, the easiest way is using the TensorFlow Lite CocoaPod releases.
See [TensorFlow Lite iOS Demo](demo_ios.md) for examples. See [TensorFlow Lite iOS Demo](ios.md) for examples.
## Building ## Building

32
tensorflow/lite/g3doc/guide/faq.md
View File

@ -11,17 +11,17 @@ detailed documentation for the topic or file a
The TensorFlow Lite converter supports the following formats: The TensorFlow Lite converter supports the following formats:
* SavedModels: * SavedModels:
[TFLiteConverter.from_saved_model](convert/python_api.md#exporting_a_savedmodel_) [TFLiteConverter.from_saved_model](../convert/python_api.md#exporting_a_savedmodel_)
* Frozen GraphDefs generated by * Frozen GraphDefs generated by
[freeze_graph.py](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/python/tools/freeze_graph.py): [freeze_graph.py](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/python/tools/freeze_graph.py):
[TFLiteConverter.from_frozen_graph](convert/python_api#exporting_a_graphdef_from_file_) [TFLiteConverter.from_frozen_graph](../convert/python_api.md#exporting_a_graphdef_from_file_)
* tf.keras HDF5 models: * tf.keras HDF5 models:
[TFLiteConverter.from_keras_model_file](convert/python_api#exporting_a_tfkeras_file_) [TFLiteConverter.from_keras_model_file](../convert/python_api.md#exporting_a_tfkeras_file_)
* tf.Session: * tf.Session:
[TFLiteConverter.from_session](python_api#exporting_a_graphdef_from_tfsession_) [TFLiteConverter.from_session](../convert/python_api.md#exporting_a_graphdef_from_tfsession_)
The recommended approach is to integrate the The recommended approach is to integrate the
[Python converter](convert/python_api.md) into your model pipeline in order to [Python converter](../convert/python_api.md) into your model pipeline in order to
detect compatibility issues early on. detect compatibility issues early on.
#### Why doesn't my model convert? #### Why doesn't my model convert?
@ -69,7 +69,7 @@ bazel run //tensorflow/lite/tools:visualize model.tflite visualized_model.html
#### Why are some operations not implemented in TensorFlow Lite? #### Why are some operations not implemented in TensorFlow Lite?
In order to keep TensorFlow Lite lightweight, only certain operations were used In order to keep TensorFlow Lite lightweight, only certain operations were used
in the converter. The [Compatibility Guide](tf_ops_compatibility.md) provides a in the converter. The [Compatibility Guide](ops_compatibility.md) provides a
list of operations currently supported by TensorFlow Lite. list of operations currently supported by TensorFlow Lite.
If you don’t see a specific operation (or an equivalent) listed, it's likely If you don’t see a specific operation (or an equivalent) listed, it's likely
@ -78,34 +78,34 @@ GitHub [issue #21526](https://github.com/tensorflow/tensorflow/issues/21526).
Leave a comment if your request hasn’t already been mentioned. Leave a comment if your request hasn’t already been mentioned.
In the meanwhile, you could try implementing a In the meanwhile, you could try implementing a
[custom operator](custom_operators.md) or using a different model that only [custom operator](ops_custom.md) or using a different model that only
contains supported operators. If binary size is not a constraint, try using contains supported operators. If binary size is not a constraint, try using
TensorFlow Lite with [select TensorFlow ops](using_select_tf_ops.md). TensorFlow Lite with [select TensorFlow ops](ops_select.md).
#### How do I test that a TensorFlow Lite model behaves the same as the original TensorFlow model? #### How do I test that a TensorFlow Lite model behaves the same as the original TensorFlow model?
The best way to test the behavior of a TensorFlow Lite model is to use our API The best way to test the behavior of a TensorFlow Lite model is to use our API
with test data and compare the outputs to TensorFlow for the same inputs. Take a with test data and compare the outputs to TensorFlow for the same inputs. Take a
look at our [Python Interpreter example](convert/python_api.md) that generates look at our [Python Interpreter example](../convert/python_api.md) that generates
random data to feed to the interpreter. random data to feed to the interpreter.
## Optimization ## Optimization
#### How do I reduce the size of my converted TensorFlow Lite model? #### How do I reduce the size of my converted TensorFlow Lite model?
[Post-training quantization](performance/post_training_quantization.md) can be [Post-training quantization](../performance/post_training_quantization.md) can be
used during conversion to TensorFlow Lite to reduce the size of the model. used during conversion to TensorFlow Lite to reduce the size of the model.
Post-training quantization quantizes weights to 8-bits of precision from Post-training quantization quantizes weights to 8-bits of precision from
floating-point and dequantizes them during runtime to perform floating point floating-point and dequantizes them during runtime to perform floating point
computations. However, note that this could have some accuracy implications. computations. However, note that this could have some accuracy implications.
If retraining the model is an option, consider If retraining the model is an option, consider
[Quantization-aware training](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/contrib/quantize/README.md). [Quantization-aware training](https://github.com/tensorflow/tensorflow/tree/r1.13/tensorflow/contrib/quantize).
However, note that quantization-aware training is only available for a subset of However, note that quantization-aware training is only available for a subset of
convolutional neural network architectures. convolutional neural network architectures.
For a deeper understanding of different optimization methods, look at For a deeper understanding of different optimization methods, look at
[Model optimization](performance/model_optimization.md). [Model optimization](../performance/model_optimization.md).
#### How do I optimize TensorFlow Lite performance for my machine learning task? #### How do I optimize TensorFlow Lite performance for my machine learning task?
@ -113,7 +113,7 @@ The high-level process to optimize TensorFlow Lite performance looks something
like this: like this:
* *Make sure that you have the right model for the task.* For image * *Make sure that you have the right model for the task.* For image
classification, check out our [list of hosted models](models.md). classification, check out our [list of hosted models](hosted_models.md).
* *Tweak the number of threads.* Many TensorFlow Lite operators support * *Tweak the number of threads.* Many TensorFlow Lite operators support
multi-threaded kernels. You can use `SetNumThreads()` in the multi-threaded kernels. You can use `SetNumThreads()` in the
[C++ API](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/interpreter.h#L345) [C++ API](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/interpreter.h#L345)
@ -124,12 +124,12 @@ like this:
Networks API, call Networks API, call
[`UseNNAPI`](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/interpreter.h#L343) [`UseNNAPI`](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/interpreter.h#L343)
on the interpreter. Or take a look at our on the interpreter. Or take a look at our
[GPU delegate tutorial](performance/gpu.md). [GPU delegate tutorial](../performance/gpu.md).
* *(Advanced) Profile Model.* The Tensorflow Lite * *(Advanced) Profile Model.* The Tensorflow Lite
[benchmarking tool](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/lite/tools/benchmark) [benchmarking tool](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/lite/tools/benchmark)
has a built-in profiler that can show per-operator statistics. If you know has a built-in profiler that can show per-operator statistics. If you know
how you can optimize an operator’s performance for your specific platform, how you can optimize an operator’s performance for your specific platform,
you can implement a [custom operator](custom_operators.md). you can implement a [custom operator](ops_custom.md).
For a more in-depth discussion on how to optimize performance, take a look at For a more in-depth discussion on how to optimize performance, take a look at
[Best Practices](performance/best_practices.md). [Best Practices](../performance/best_practices.md).

34
tensorflow/lite/g3doc/guide/get_started.md
View File

@ -35,7 +35,7 @@ by suggesting contextually relevant messages. The model is built specifically fo
memory constrained devices, such as watches and phones, and has been successfully memory constrained devices, such as watches and phones, and has been successfully
used in Smart Replies on Android Wear. Currently, this model is Android-specific. used in Smart Replies on Android Wear. Currently, this model is Android-specific.
These pre-trained models are [available for download](models.md). These pre-trained models are [available for download](hosted_models.md).
### Re-train Inception-V3 or MobileNet for a custom data set ### Re-train Inception-V3 or MobileNet for a custom data set
@ -63,24 +63,24 @@ the framework. See
to create file for the custom model. to create file for the custom model.
TensorFlow Lite currently supports a subset of TensorFlow operators. Refer to TensorFlow Lite currently supports a subset of TensorFlow operators. Refer to
the [TensorFlow Lite & TensorFlow Compatibility Guide](tf_ops_compatibility.md) the [TensorFlow Lite & TensorFlow Compatibility Guide](ops_compatibility.md)
for supported operators and their usage. This set of operators will continue to for supported operators and their usage. This set of operators will continue to
grow in future Tensorflow Lite releases. grow in future Tensorflow Lite releases.
## 2. Convert the model format ## 2. Convert the model format
The [TensorFlow Lite Converter](convert/index.md) accepts the following file The [TensorFlow Lite Converter](../convert.md) accepts the following file
formats: formats:
* `SavedModel` — A `GraphDef` and checkpoint with a signature that labels * `SavedModel` — A `GraphDef` and checkpoint with a signature that labels
input and output arguments to a model. See the documentation for converting input and output arguments to a model. See the documentation for converting
SavedModels using [Python](convert/python_api.md#basic_savedmodel) or using SavedModels using [Python](../convert/python_api.md#basic_savedmodel) or using
the [command line](convert/cmdline_examples.md#savedmodel). the [command line](../convert/cmdline_examples.md#savedmodel).
* `tf.keras` - A HDF5 file containing a model with weights and input and * `tf.keras` - A HDF5 file containing a model with weights and input and
output arguments generated by `tf.Keras`. See the documentation for output arguments generated by `tf.Keras`. See the documentation for
converting HDF5 models using converting HDF5 models using
[Python](convert/python_api.md#basic_keras_file) or using the [Python](../convert/python_api.md#basic_keras_file) or using the
[command line](convert/cmdline_examples.md#keras). [command line](../convert/cmdline_examples.md#keras).
* `frozen tf.GraphDef` — A subclass of `tf.GraphDef` that does not contain * `frozen tf.GraphDef` — A subclass of `tf.GraphDef` that does not contain
variables. A `GraphDef` can be converted to a `frozen GraphDef` by taking a variables. A `GraphDef` can be converted to a `frozen GraphDef` by taking a
checkpoint and a `GraphDef`, and converting each variable into a constant checkpoint and a `GraphDef`, and converting each variable into a constant
@ -154,9 +154,9 @@ the arguments for specifying the output nodes for inference in the
### Full converter reference ### Full converter reference
The [TensorFlow Lite Converter](convert/index.md) can be The [TensorFlow Lite Converter](../convert.md) can be
[Python](convert/python_api.md) or from the [Python](../convert/python_api.md) or from the
[command line](convert/cmdline_examples.md). This allows you to integrate the [command line](../convert/cmdline_examples.md). This allows you to integrate the
conversion step into the model design workflow, ensuring the model is easy to conversion step into the model design workflow, ensuring the model is easy to
convert to a mobile inference graph. convert to a mobile inference graph.
@ -195,15 +195,15 @@ The open source Android demo app uses the JNI interface and is available
[on GitHub](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/lite/java/demo/app). [on GitHub](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/lite/java/demo/app).
You can also download a You can also download a
[prebuilt APK](http://download.tensorflow.org/deps/tflite/TfLiteCameraDemo.apk). [prebuilt APK](http://download.tensorflow.org/deps/tflite/TfLiteCameraDemo.apk).
See the <a href="./demo_android.md">Android demo</a> guide for details. See the <a href="./android.md">Android demo</a> guide for details.
The <a href="./android_build.md">Android mobile</a> guide has instructions for The <a href="./android.md">Android mobile</a> guide has instructions for
installing TensorFlow on Android and setting up `bazel` and Android Studio. installing TensorFlow on Android and setting up `bazel` and Android Studio.
### iOS ### iOS
To integrate a TensorFlow model in an iOS app, see the To integrate a TensorFlow model in an iOS app, see the
[TensorFlow Lite for iOS](ios.md) guide and <a href="./demo_ios.md">iOS demo</a> [TensorFlow Lite for iOS](ios.md) guide and <a href="./ios.md">iOS demo</a>
guide. guide.
#### Core ML support #### Core ML support
@ -218,9 +218,9 @@ devices. To use the converter, refer to the
### ARM32 and ARM64 Linux ### ARM32 and ARM64 Linux
Compile Tensorflow Lite for a Raspberry Pi by following the Compile Tensorflow Lite for a Raspberry Pi by following the
[RPi build instructions](rpi.md) Compile Tensorflow Lite for a generic aarch64 [RPi build instructions](build_rpi.md) Compile Tensorflow Lite for a generic aarch64
board such as Odroid C2, Pine64, NanoPi, and others by following the board such as Odroid C2, Pine64, NanoPi, and others by following the
[ARM64 Linux build instructions](linux_aarch64.md) This compiles a static [ARM64 Linux build instructions](build_arm64.md) This compiles a static
library file (`.a`) used to build your app. There are plans for Python bindings library file (`.a`) used to build your app. There are plans for Python bindings
and a demo app. and a demo app.
@ -253,7 +253,7 @@ tflite_quantized_model=converter.convert()
open(“quantized_model.tflite”, “wb”).write(tflite_quantized_model) open(“quantized_model.tflite”, “wb”).write(tflite_quantized_model)
``` ```
Read the full documentation [here](performance/post_training_quantization.md) Read the full documentation [here](../performance/post_training_quantization.md)
and see a tutorial and see a tutorial
[here](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/tutorials/post_training_quant.ipynb). [here](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/tutorials/post_training_quant.ipynb).
@ -268,4 +268,4 @@ Another benefit with GPU inference is its power efficiency. GPUs carry out the
computations in a very efficient and optimized manner, so that they consume less computations in a very efficient and optimized manner, so that they consume less
power and generate less heat than when the same task is run on CPUs. power and generate less heat than when the same task is run on CPUs.
Read the tutorial [here](performance/gpu) and full documentation [here](performance/gpu_advanced). Read the tutorial [here](../performance/gpu.md) and full documentation [here](../performance/gpu_advanced.md).

14
tensorflow/lite/g3doc/guide/hosted_models.md
View File

@ -3,7 +3,7 @@
The following is an incomplete list of pre-trained models optimized to work with The following is an incomplete list of pre-trained models optimized to work with
TensorFlow Lite. TensorFlow Lite.
To get started choosing a model, visit <a href="./">Models</a>. To get started choosing a model, visit <a href="../models">Models</a>.
Note: The best model for a given application depends on your requirements. For Note: The best model for a given application depends on your requirements. For
example, some applications might benefit from higher accuracy, while others example, some applications might benefit from higher accuracy, while others
@ -13,7 +13,7 @@ models to find the optimal balance between size, performance, and accuracy.
## Image classification ## Image classification
For more information about image classification, see For more information about image classification, see
<a href="image_classification/overview.md">Image classification</a>. <a href="../image_classification/overview.md">Image classification</a>.
### Quantized models ### Quantized models
@ -50,7 +50,7 @@ Graph.
Note: Performance numbers were benchmarked on Pixel-2 using single thread large Note: Performance numbers were benchmarked on Pixel-2 using single thread large
core. Accuracy numbers were computed using the core. Accuracy numbers were computed using the
[TFLite accuracy tool](../tools/accuracy/ilsvrc.md). [TFLite accuracy tool](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/lite/tools/accuracy/ilsvrc).
### Floating point models ### Floating point models
@ -108,7 +108,7 @@ BIG core.
## Object detection ## Object detection
For more information about object detection, see For more information about object detection, see
<a href="object_detection/overview.md">Object detection</a>. <a href="../models/object_detection/overview.md">Object detection</a>.
The object detection model we currently host is The object detection model we currently host is
**coco_ssd_mobilenet_v1_1.0_quant_2018_06_29**. **coco_ssd_mobilenet_v1_1.0_quant_2018_06_29**.
@ -119,7 +119,7 @@ model and labels</a>
## Pose estimation ## Pose estimation
For more information about pose estimation, see For more information about pose estimation, see
<a href="pose_estimation/overview.md">Pose estimation</a>. <a href="../models/pose_estimation/overview.md">Pose estimation</a>.
The pose estimation model we currently host is The pose estimation model we currently host is
**multi_person_mobilenet_v1_075_float**. **multi_person_mobilenet_v1_075_float**.
@ -130,7 +130,7 @@ model</a>
## Image segmentation ## Image segmentation
For more information about image segmentation, see For more information about image segmentation, see
<a href="segmentation/overview.md">Segmentation</a>. <a href="../models/segmentation/overview.md">Segmentation</a>.
The image segmentation model we currently host is **deeplabv3_257_mv_gpu**. The image segmentation model we currently host is **deeplabv3_257_mv_gpu**.
@ -140,7 +140,7 @@ model</a>
## Smart reply ## Smart reply
For more information about smart reply, see For more information about smart reply, see
<a href="smart_reply/overview.md">Smart reply</a>. <a href="../models/smart_reply/overview.md">Smart reply</a>.
The smart reply model we currently host is **smartreply_1.0_2017_11_01**. The smart reply model we currently host is **smartreply_1.0_2017_11_01**.

2
tensorflow/lite/g3doc/guide/index.md
View File

@ -118,7 +118,7 @@ TensorFlow Lite provides:
to all first-party and third-party apps. to all first-party and third-party apps.
Also see the complete list of Also see the complete list of
[TensorFlow Lite's supported models](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/g3doc/models.md), [TensorFlow Lite's supported models](hosted_models.md),
including the model sizes, performance numbers, and downloadable model files. including the model sizes, performance numbers, and downloadable model files.
- Quantized versions of the MobileNet model, which runs faster than the - Quantized versions of the MobileNet model, which runs faster than the

12
tensorflow/lite/g3doc/guide/inference.md
View File

@ -7,7 +7,7 @@
TensorFlow Lite inference is the process of executing a TensorFlow Lite TensorFlow Lite inference is the process of executing a TensorFlow Lite
model on-device and extracting meaningful results from it. Inference is the model on-device and extracting meaningful results from it. Inference is the
final step in using the model on-device in the final step in using the model on-device in the
[architecture](./index.md#tensorflow_lite_architecture). [architecture](index.md#tensorflow_lite_architecture).
Inference for TensorFlow Lite models is run through an interpreter. This Inference for TensorFlow Lite models is run through an interpreter. This
document outlines the various APIs for the interpreter along with the document outlines the various APIs for the interpreter along with the
@ -51,14 +51,14 @@ On Android, TensorFlow Lite inference can be performed using either Java or C++
APIs. The Java APIs provide convenience and can be used directly within your APIs. The Java APIs provide convenience and can be used directly within your
Android Activity classes. The C++ APIs on the other hand may offer more Android Activity classes. The C++ APIs on the other hand may offer more
flexibility and speed, but may require writing JNI wrappers to move data between flexibility and speed, but may require writing JNI wrappers to move data between
Java and C++ layers. You can find an example [here](./android.md). Java and C++ layers. You can find an example [here](android.md).
#### iOS #### iOS
TensorFlow Lite provides Swift/Objective C++ APIs for inference on iOS. An TensorFlow Lite provides Swift/Objective C++ APIs for inference on iOS. An
example can be found [here](./ios.md). example can be found [here](ios.md).
#### Linux #### Linux
On Linux platforms such as [Raspberry Pi](./build_rpi.md), TensorFlow Lite C++ On Linux platforms such as [Raspberry Pi](build_rpi.md), TensorFlow Lite C++
and Python APIs can be used to run inference. and Python APIs can be used to run inference.
@ -72,7 +72,7 @@ should be no surprise that the APIs try to avoid unnecessary copies at the
expense of convenience. Similarly, consistency with TensorFlow APIs was not an expense of convenience. Similarly, consistency with TensorFlow APIs was not an
explicit goal and some variance is to be expected. explicit goal and some variance is to be expected.
There is also a [Python API for TensorFlow Lite](./../convert/python_api.md). There is also a [Python API for TensorFlow Lite](../convert/python_api.md).
### Loading a Model ### Loading a Model
@ -205,7 +205,7 @@ where each entry in `inputs` corresponds to an input tensor and
`map_of_indices_to_outputs` maps indices of output tensors to the corresponding `map_of_indices_to_outputs` maps indices of output tensors to the corresponding
output data. In both cases the tensor indices should correspond to the values output data. In both cases the tensor indices should correspond to the values
given to the given to the
[TensorFlow Lite Optimized Converter](./../convert/cmdline_examples.md) when the [TensorFlow Lite Optimized Converter](../convert/cmdline_examples.md) when the
model was created. Be aware that the order of tensors in `input` must match the model was created. Be aware that the order of tensors in `input` must match the
order given to the `TensorFlow Lite Optimized Converter`. order given to the `TensorFlow Lite Optimized Converter`.

6
tensorflow/lite/g3doc/guide/ios.md
View File

@ -79,16 +79,16 @@ Under `Project navigator -> tflite_camera_example -> Targets ->
tflite_camera_example -> General` change the bundle identifier by pre-pending tflite_camera_example -> General` change the bundle identifier by pre-pending
your name: your name:
![pre-pend your name to the bundle identifier](images/ios/bundle_identifier.png) ![pre-pend your name to the bundle identifier](../images/ios/bundle_identifier.png)
Plug in your iOS device. Note the app must be executed with a real device with Plug in your iOS device. Note the app must be executed with a real device with
camera. Select the iOS device from the drop-down menu. camera. Select the iOS device from the drop-down menu.
![Device selection](images/ios/device_selection.png) ![Device selection](../images/ios/device_selection.png)
Click the "Run" button to build and run the app Click the "Run" button to build and run the app
![Build and execute](images/ios/build_and_execute.png) ![Build and execute](../images/ios/build_and_execute.png)
Note that as mentioned earlier, you must already have a device set up and linked Note that as mentioned earlier, you must already have a device set up and linked
to your Apple Developer account in order to deploy the app on a device. to your Apple Developer account in order to deploy the app on a device.

4
tensorflow/lite/g3doc/guide/ops_compatibility.md
View File

@ -9,7 +9,7 @@ Since the set of TensorFlow Lite operations is smaller than TensorFlow's, not
every model is convertible. Even for supported operations, very specific usage every model is convertible. Even for supported operations, very specific usage
patterns are sometimes expected, for performance reasons. We expect to expand patterns are sometimes expected, for performance reasons. We expect to expand
the set of supported operations in future TensorFlow Lite releases. Additional the set of supported operations in future TensorFlow Lite releases. Additional
ops can be included by [using select TensorFlow ops](using_select_tf_ops.md), at ops can be included by [using select TensorFlow ops](ops_select.md), at
the cost of binary size. the cost of binary size.
The best way to understand how to build a TensorFlow model that can be used with The best way to understand how to build a TensorFlow model that can be used with
@ -27,7 +27,7 @@ between floating-point and quantized models lies in the way they are converted.
Quantized conversion requires dynamic range information for tensors. This Quantized conversion requires dynamic range information for tensors. This
requires "fake-quantization" during model training, getting range information requires "fake-quantization" during model training, getting range information
via a calibration data set, or doing "on-the-fly" range estimation. See via a calibration data set, or doing "on-the-fly" range estimation. See
[quantization](performance/model_optimization.md). [quantization](../performance/model_optimization.md).
## Data Format and Broadcasting ## Data Format and Broadcasting

8
tensorflow/lite/g3doc/guide/ops_select.md
View File

@ -15,7 +15,7 @@ please send feedback about models that work and issues you are facing to
tflite@tensorflow.org. tflite@tensorflow.org.
TensorFlow Lite will continue to have TensorFlow Lite will continue to have
[TensorFlow Lite builtin ops](tf_ops_compatibility.md) optimized for mobile and [TensorFlow Lite builtin ops](ops_compatibility.md) optimized for mobile and
embedded devices. However, TensorFlow Lite models can now use a subset of embedded devices. However, TensorFlow Lite models can now use a subset of
TensorFlow ops when TFLite builtin ops are not sufficient. TensorFlow ops when TFLite builtin ops are not sufficient.
@ -34,7 +34,7 @@ choice. It also discusses some [known limitations](#known-limitations), the
To convert a TensorFlow model to a TensorFlow Lite model with TensorFlow ops, To convert a TensorFlow model to a TensorFlow Lite model with TensorFlow ops,
use the `target_ops` argument in the use the `target_ops` argument in the
[TensorFlow Lite converter](https://www.tensorflow.org/lite/convert/). The [TensorFlow Lite converter](../convert/index.md). The
following values are valid options for `target_ops`: following values are valid options for `target_ops`:
* `TFLITE_BUILTINS` - Converts models using TensorFlow Lite builtin ops. * `TFLITE_BUILTINS` - Converts models using TensorFlow Lite builtin ops.
@ -64,7 +64,7 @@ open("converted_model.tflite", "wb").write(tflite_model)
``` ```
The following example shows how to use `target_ops` in the The following example shows how to use `target_ops` in the
[`tflite_convert`](https://www.tensorflow.org/lite/convert/cmdline_examples) [`tflite_convert`](../convert/cmdline_examples.md)
command line tool. command line tool.
``` ```
@ -97,7 +97,7 @@ includes the necessary library of TensorFlow ops.
### Android AAR ### Android AAR
A new Android AAR target with select TensorFlow ops has been added for A new Android AAR target with select TensorFlow ops has been added for
convenience. Assuming a <a href="./demo_android.md">working TensorFlow Lite convenience. Assuming a <a href="android.md">working TensorFlow Lite
build environment</a>, build the Android AAR with select TensorFlow ops as build environment</a>, build the Android AAR with select TensorFlow ops as
follows: follows:

20
tensorflow/lite/g3doc/models/image_classification/overview.md
View File

@ -15,14 +15,14 @@ If you understand image classification, you’re new to TensorFlow Lite, and
you’re working with Android or iOS, we recommend following the corresponding you’re working with Android or iOS, we recommend following the corresponding
tutorial that will walk you through our sample code. tutorial that will walk you through our sample code.
<a class="button button-primary" href="android">Android</a> <a class="button button-primary" href="android.md">Android</a>
<a class="button button-primary" href="ios">iOS</a> <a class="button button-primary" href="ios.md">iOS</a>
We also provide <a href="example_applications">example applications</a> you can We also provide <a href="example_applications">example applications</a> you can
use to get started. use to get started.
If you are using a platform other than Android or iOS, or you are already If you are using a platform other than Android or iOS, or you are already
familiar with the <a href="../../apis">TensorFlow Lite APIs</a>, you can familiar with the <a href="https://www.tensorflow.org/api_docs/python/tf/lite">TensorFlow Lite APIs</a>, you can
download our starter image classification model and the accompanying labels. download our starter image classification model and the accompanying labels.
<a class="button button-primary" href="https://storage.googleapis.com/download.tensorflow.org/models/tflite/mobilenet_v1_1.0_224_quant_and_labels.zip">Download <a class="button button-primary" href="https://storage.googleapis.com/download.tensorflow.org/models/tflite/mobilenet_v1_1.0_224_quant_and_labels.zip">Download
@ -34,7 +34,7 @@ performance, accuracy, and model size. For guidance, see
<a href="#choose_a_different_model">Choose a different model</a>. <a href="#choose_a_different_model">Choose a different model</a>.
If you are using a platform other than Android or iOS, or you are already If you are using a platform other than Android or iOS, or you are already
familiar with the <a href="../../apis.md">TensorFlow Lite APIs</a>, you can familiar with the <a href="https://www.tensorflow.org/api_docs/python/tf/lite">TensorFlow Lite APIs</a>, you can
download our starter image classification model and the accompanying labels. download our starter image classification model and the accompanying labels.
<a class="button button-primary" href="https://storage.googleapis.com/download.tensorflow.org/models/tflite/mobilenet_v1_1.0_224_quant_and_labels.zip">Download <a class="button button-primary" href="https://storage.googleapis.com/download.tensorflow.org/models/tflite/mobilenet_v1_1.0_224_quant_and_labels.zip">Download
@ -46,7 +46,7 @@ We have example applications for image classification for both Android and iOS.
<a class="button button-primary" href="https://github.com/tensorflow/examples/tree/master/lite/examples/image_classification/android">Android <a class="button button-primary" href="https://github.com/tensorflow/examples/tree/master/lite/examples/image_classification/android">Android
example</a> example</a>
<a class="button button-primary" href="https://github.com/tensorflow/examples/tree/master/lite/examples/image_classification/ios">iOS <a class="button button-primary" href="https://github.com/tensorflow/examples/tree/master/lite/examples/image_classification/ios.md">iOS
example</a> example</a>
The following screenshot shows the Android image classification example: The following screenshot shows the Android image classification example:
@ -204,8 +204,8 @@ If you want to train a model to recognize new classes, see
For the following use cases, you should use a different type of model: For the following use cases, you should use a different type of model:
<ul> <ul>
<li>Predicting the type and position of one or more objects within an image (see <a href="object_detection">object detection</a>)</li> <li>Predicting the type and position of one or more objects within an image (see <a href="../object_detection/overview.md">object detection</a>)</li>
<li>Predicting the composition of an image, for example subject versus background (see <a href="segmentation">segmentation</a>)</li> <li>Predicting the composition of an image, for example subject versus background (see <a href="../segmentation/overview.md">segmentation</a>)</li>
</ul> </ul>
Once you have the starter model running on your target device, you can Once you have the starter model running on your target device, you can
@ -239,7 +239,7 @@ We measure accuracy in terms of how often the model correctly classifies an
image. For example, a model with a stated accuracy of 60% can be expected to image. For example, a model with a stated accuracy of 60% can be expected to
classify an image correctly an average of 60% of the time. classify an image correctly an average of 60% of the time.
Our <a href="../hosted.md">List of hosted models</a> provides Top-1 and Top-5 Our <a href="../../guide/hosted_models.md">list of hosted models</a> provides Top-1 and Top-5
accuracy statistics. Top-1 refers to how often the correct label appears as the accuracy statistics. Top-1 refers to how often the correct label appears as the
label with the highest probability in the model’s output. Top-5 refers to how label with the highest probability in the model’s output. Top-5 refers to how
often the correct label appears in the top 5 highest probabilities in the often the correct label appears in the top 5 highest probabilities in the
@ -258,14 +258,14 @@ Our quantized Mobilenet models’ size ranges from 0.5 to 3.4 Mb.
### Architecture ### Architecture
There are several different architectures of models available on There are several different architectures of models available on
<a href="../hosted.md">List of hosted models</a>, indicated by the model’s name. <a href="../../guide/hosted_models.md">List of hosted models</a>, indicated by the model’s name.
For example, you can choose between Mobilenet, Inception, and others. For example, you can choose between Mobilenet, Inception, and others.
The architecture of a model impacts its performance, accuracy, and size. All of The architecture of a model impacts its performance, accuracy, and size. All of
our hosted models are trained on the same data, meaning you can use the provided our hosted models are trained on the same data, meaning you can use the provided
statistics to compare them and choose which is optimal for your application. statistics to compare them and choose which is optimal for your application.
Note: The image classification models we provide accept varying sizes of input. For some models, this is indicated in the filename. For example, the Mobilenet_V1_1.0_224 model accepts an input of 224x224 pixels. <br /><br />All of the models require three color channels per pixel (red, green, and blue). Quantized models require 1 byte per channel, and float models require 4 bytes per channel.<br /><br />Our <a href="android.md">Android</a> and <a href="ios">iOS</a> code samples demonstrate how to process full-sized camera images into the required format for each model. Note: The image classification models we provide accept varying sizes of input. For some models, this is indicated in the filename. For example, the Mobilenet_V1_1.0_224 model accepts an input of 224x224 pixels. <br /><br />All of the models require three color channels per pixel (red, green, and blue). Quantized models require 1 byte per channel, and float models require 4 bytes per channel.<br /><br />Our <a href="android.md">Android</a> and <a href="ios.md">iOS</a> code samples demonstrate how to process full-sized camera images into the required format for each model.
## Customize model ## Customize model

2
tensorflow/lite/g3doc/models/object_detection/overview.md
View File

@ -17,7 +17,7 @@ example</a>
example</a> example</a>
If you are using a platform other than Android or iOS, or you are already If you are using a platform other than Android or iOS, or you are already
familiar with the <a href="../apis.md">TensorFlow Lite APIs</a>, you can familiar with the <a href="https://www.tensorflow.org/api_docs/python/tf/lite">TensorFlow Lite APIs</a>, you can
download our starter object detection model and the accompanying labels. download our starter object detection model and the accompanying labels.
<a class="button button-primary" href="http://storage.googleapis.com/download.tensorflow.org/models/tflite/coco_ssd_mobilenet_v1_1.0_quant_2018_06_29.zip">Download <a class="button button-primary" href="http://storage.googleapis.com/download.tensorflow.org/models/tflite/coco_ssd_mobilenet_v1_1.0_quant_2018_06_29.zip">Download

4
tensorflow/lite/g3doc/performance/post_training_quantization.md
View File

@ -3,7 +3,7 @@
Post-training quantization is a general technique to reduce model size while also Post-training quantization is a general technique to reduce model size while also
providing up to 3x lower latency with little degradation in model accuracy. Post-training providing up to 3x lower latency with little degradation in model accuracy. Post-training
quantization quantizes weights from floating point to 8-bits of precision. This technique quantization quantizes weights from floating point to 8-bits of precision. This technique
is enabled as an option in the [TensorFlow Lite converter](../convert): is enabled as an option in the [TensorFlow Lite converter](../convert/index.md):
``` ```
import tensorflow as tf import tensorflow as tf
@ -31,7 +31,7 @@ Hybrid ops are available for the most compute-intensive operators in a network:
Since weights are quantized post training, there could be an accuracy loss, particularly for Since weights are quantized post training, there could be an accuracy loss, particularly for
smaller networks. Pre-trained fully quantized models are provided for specific networks in smaller networks. Pre-trained fully quantized models are provided for specific networks in
the [TensorFlow Lite model repository](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/g3doc/models.md#image-classification-quantized-models){:.external}. It is important to check the accuracy of the quantized model to verify that any degradation the [TensorFlow Lite model repository](../models/). It is important to check the accuracy of the quantized model to verify that any degradation
in accuracy is within acceptable limits. There is a tool to evaluate [TensorFlow Lite model accuracy](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/tools/accuracy/README.md){:.external}. in accuracy is within acceptable limits. There is a tool to evaluate [TensorFlow Lite model accuracy](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/tools/accuracy/README.md){:.external}.
If the accuracy drop is too high, consider using [quantization aware training](https://github.com/tensorflow/tensorflow/tree/r1.13/tensorflow/contrib/quantize){:.external}. If the accuracy drop is too high, consider using [quantization aware training](https://github.com/tensorflow/tensorflow/tree/r1.13/tensorflow/contrib/quantize){:.external}.