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

Updates Swift and ObjC READMEs and quickstart.

Browse Source 
PiperOrigin-RevId: 247513844
This commit is contained in:
A. Unique TensorFlower 2019-05-09 16:03:59 -07:00 committed by TensorFlower Gardener
parent 3eb4a44f05
commit 6f980870f3
5 changed files with 69 additions and 65 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

67
tensorflow/lite/experimental/objc/README.md
View File

@ -5,7 +5,7 @@ solution for Objective-C developers. It enables low-latency inference of
on-device machine learning models with a small binary size and fast performance
supporting hardware acceleration.
## Getting Started
## Build TensorFlow with iOS support
To build the Objective-C TensorFlow Lite library on Apple platforms,
[install from source](https://www.tensorflow.org/install/source#setup_for_linux_and_macos)
@ -19,9 +19,34 @@ python configure.py
Follow the prompts and when asked to build TensorFlow with iOS support, enter `y`.
### Bazel
### CocoaPods developers
In your `BUILD` file, add the `TensorFlowLite` dependency:
Add the TensorFlow Lite pod to your `Podfile`:
```ruby
pod 'TensorFlowLiteObjC'
```
Then, run `pod install`.
In your Objective-C files, import the umbrella header:
```objectivec
#import "TFLTensorFlowLite.h"
```
Or, the module if you set `CLANG_ENABLE_MODULES = YES` in your Xcode project:
```objectivec
@import TFLTensorFlowLite;
```
Note: To import the TensorFlow Lite module in your Objective-C files, you must
also include `use_frameworks!` in your `Podfile`.
### Bazel developers
In your `BUILD` file, add the `TensorFlowLite` dependency to your target:
```python
objc_library(
@ -37,6 +62,12 @@ In your Objective-C files, import the umbrella header:
#import "TFLTensorFlowLite.h"
```
Or, the module if you set `CLANG_ENABLE_MODULES = YES` in your Xcode project:
```objectivec
@import TFLTensorFlowLite;
```
Build the `TensorFlowLite` Objective-C library target:
```shell
@ -49,36 +80,14 @@ Build the `TensorFlowLiteTests` target:
bazel test tensorflow/lite/experimental/objc:TensorFlowLiteTests
```
### Tulsi
#### Generate the Xcode project using Tulsi
Open the `TensorFlowLite.tulsiproj` using the
[TulsiApp](https://github.com/bazelbuild/tulsi) or by running the
Open the `//tensorflow/lite/experimental/objc/TensorFlowLite.tulsiproj` using
the [TulsiApp](https://github.com/bazelbuild/tulsi)
or by running the
[`generate_xcodeproj.sh`](https://github.com/bazelbuild/tulsi/blob/master/src/tools/generate_xcodeproj.sh)
script from the root `tensorflow` directory:
```shell
generate_xcodeproj.sh --genconfig tensorflow/lite/experimental/objc/TensorFlowLite.tulsiproj:TensorFlowLite --outputfolder ~/path/to/generated/TensorFlowLite.xcodeproj
```
### CocoaPods
Add the following to your `Podfile`:
```ruby
pod 'TensorFlowLiteObjC'
```
Then, run `pod install`.
In your Objective-C files, import the umbrella header:
```objectivec
#import "TFLTensorFlowLite.h"
```
Or, the module if `CLANG_ENABLE_MODULES = YES` and `use_frameworks!` is
specified in your `Podfile`:
```objectivec
@import TFLTensorFlowLite;
```

2
tensorflow/lite/experimental/objc/TensorFlowLiteObjC.podspec
View File

@ -1,5 +1,3 @@
# Run `pod lib lint TensorFlowLiteObjC.podspec` to ensure this is a valid spec.
Pod::Spec.new do |s|
s.name = 'TensorFlowLiteObjC'
s.version = '0.2.0'

46
tensorflow/lite/experimental/swift/README.md
View File

@ -5,7 +5,7 @@ solution for Swift developers. It enables low-latency inference of on-device
machine learning models with a small binary size and fast performance supporting
hardware acceleration.
## Getting Started
## Build TensorFlow with iOS support
To build the Swift TensorFlow Lite library on Apple platforms,
[install from source](https://www.tensorflow.org/install/source#setup_for_linux_and_macos)
@ -19,9 +19,25 @@ python configure.py
Follow the prompts and when asked to build TensorFlow with iOS support, enter `y`.
### Bazel
### CocoaPods developers
In your `BUILD` file, add the `TensorFlowLite` dependency:
Add the TensorFlow Lite pod to your `Podfile`:
```ruby
pod 'TensorFlowLiteSwift'
```
Then, run `pod install`.
In your Swift files, import the module:
```swift
import TensorFlowLite
```
### Bazel developers
In your `BUILD` file, add the `TensorFlowLite` dependency to your target:
```python
swift_library(
@ -49,12 +65,12 @@ Build the `TensorFlowLiteTests` target:
bazel test tensorflow/lite/experimental/swift:TensorFlowLiteTests --swiftcopt=-enable-testing
```
Note that `--swiftcopt=-enable-testing` is required for optimized builds (`-c opt`).
Note: `--swiftcopt=-enable-testing` is required for optimized builds (`-c opt`).
### Tulsi
#### Generate the Xcode project using Tulsi
Open the `TensorFlowLite.tulsiproj` using the
[TulsiApp](https://github.com/bazelbuild/tulsi)
Open the `//tensorflow/lite/experimental/swift/TensorFlowLite.tulsiproj` using
the [TulsiApp](https://github.com/bazelbuild/tulsi)
or by running the
[`generate_xcodeproj.sh`](https://github.com/bazelbuild/tulsi/blob/master/src/tools/generate_xcodeproj.sh)
script from the root `tensorflow` directory:
@ -62,19 +78,3 @@ script from the root `tensorflow` directory:
```shell
generate_xcodeproj.sh --genconfig tensorflow/lite/experimental/swift/TensorFlowLite.tulsiproj:TensorFlowLite --outputfolder ~/path/to/generated/TensorFlowLite.xcodeproj
```
### CocoaPods
Add the following to your `Podfile`:
```ruby
pod 'TensorFlowLiteSwift'
```
Then, run `pod install`.
In your Swift files, import the module:
```swift
import TensorFlowLite
```

2
tensorflow/lite/experimental/swift/TensorFlowLiteSwift.podspec
View File

@ -1,5 +1,3 @@
# Run `pod lib lint TensorFlowLiteSwift.podspec` to ensure this is a valid spec.
Pod::Spec.new do |s|
s.name = 'TensorFlowLiteSwift'
s.version = '0.2.0'

17
tensorflow/lite/g3doc/guide/ios.md
View File

@ -30,12 +30,12 @@ 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)
as a starting point.
The sections below walk you through the steps for adding TensorFlow Lite Swift
or Objective-C to your project:
The sections below demonstrate how to add TensorFlow Lite Swift or Objective-C
to your project:
### CocoaPods developers
In your `Podfile`, add the TensorFlow Lite pod. Then, run `pod install`:
In your `Podfile`, add the TensorFlow Lite pod. Then, run `pod install`.
#### Swift
@ -52,7 +52,7 @@ pod 'TensorFlowLiteObjC'
### Bazel developers
In your `BUILD` file, add the `TensorFlowLite` dependency.
In your `BUILD` file, add the `TensorFlowLite` dependency to your target.
#### Swift
@ -74,7 +74,7 @@ objc_library(
)
```
### Importing the library
### Import the library
For Swift files, import the TensorFlow Lite module:
@ -88,12 +88,11 @@ For Objective-C files, import the umbrella header:
#import "TFLTensorFlowLite.h"
```
Or, the TensorFlow Lite module:
Or, the module if you set `CLANG_ENABLE_MODULES = YES` in your Xcode project:
```objectivec
@import TFLTensorFlowLite;
```
Note: If importing the Objective-C TensorFlow Lite module, `CLANG_ENABLE_MODULES`
must be set to `YES`. Additionally, for CocoaPods developers, `use_frameworks!`
must be specified in your `Podfile`.
Note: For CocoaPods developers who want to import the Objective-C TensorFlow
Lite module, you must also include `use_frameworks!` in your `Podfile`.