@tensorflow/tfjs-converter - npm Package Compare versions

Comparing version 0.2.1 to 0.3.0

dist/operations/op_list/convolution.json

@@ -175,3 +175,3 @@ [
   {
-    "tfOpName": "Conv2DTranspose",
+    "tfOpName": "Conv2DBackpropInput",
     "dlOpName": "conv2dTranspose",
@@ -191,3 +191,3 @@ "category": "convolution",
       {
-        "tfParamName": "output_shape",
+        "tfInputIndex": 2,
         "dlParamName": "outputShape",
@@ -194,0 +194,0 @@ "type": "number[]"

dist/version.d.ts

@@ -1,2 +0,2 @@
-declare const version = "0.2.1";
+declare const version = "0.3.0";
 export { version };

dist/version.js

 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
-var version = '0.2.1';
+var version = '0.3.0';
 exports.version = version;
 //# sourceMappingURL=version.js.map

package.json

 {
   "name": "@tensorflow/tfjs-converter",
-  "version": "0.2.1",
+  "version": "0.3.0",
   "description": "Tensorflow model converter for javascript",
@@ -15,6 +15,6 @@ "main": "dist/index.js",
   "peerDependencies": {
-    "@tensorflow/tfjs-core": "0.9.0"
+    "@tensorflow/tfjs-core": "0.9.1"
   },
   "devDependencies": {
-    "@tensorflow/tfjs-core": "0.9.0",
+    "@tensorflow/tfjs-core": "0.9.1",
     "@types/jasmine": "~2.8.6",
@@ -21,0 +21,0 @@ "@types/seedrandom": "~2.4.27",

README.md

@@ -6,4 +6,3 @@ [![Build Status](https://travis-ci.org/tensorflow/tfjs-converter.svg?branch=master)](https://travis-ci.org/tensorflow/tfjs-converter)
 **TensorFlow.js converter** is an open source library to load a pretrained
-TensorFlow [SavedModel](https://www.tensorflow.org/programmers_guide/saved_model#overview_of_saving_and_restoring_models)
-or [Session Bundle](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/contrib/session_bundle/README.md)
+TensorFlow [SavedModel](https://www.tensorflow.org/programmers_guide/saved_model#overview_of_saving_and_restoring_models), [Frozen Model](https://www.tensorflow.org/mobile/prepare_models#how_do_you_get_a_model_you_can_use_on_mobile) or [Session Bundle](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/contrib/session_bundle/README.md)
 into the browser and run inference through [TensorFlow.js](https://js.tensorflow.org).
@@ -15,6 +14,6 @@
 
-1. A python pip package to convert a TensorFlow SavedModel/Session Bundle to a web friendly format. If you already have a converted model, or are using an already hosted model (e.g. MobileNet), skip this step.
+1. A python pip package to convert a TensorFlow SavedModel/Frozen Model/Session Bundle to a web friendly format. If you already have a converted model, or are using an already hosted model (e.g. MobileNet), skip this step.
 2. [Javascript API](./src/executor/tf_model.ts), for loading and running inference.
 
-## Step 1: Converting a [SavedModel](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/python/saved_model/README.md) or [Session Bundle](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/contrib/session_bundle/README.md) to a web-friendly format
+## Step 1: Converting a [SavedModel](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/python/saved_model/README.md), [Session Bundle](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/contrib/session_bundle/README.md), [Frozen Model](https://www.tensorflow.org/mobile/prepare_models#how_do_you_get_a_model_you_can_use_on_mobile) or [Tensorflow Hub module](https://www.tensorflow.org/hub/) to a web-friendly format
 
@@ -37,3 +36,3 @@ 1. Install the TensorFlow.js pip package:
     --output_node_names='MobilenetV1/Predictions/Reshape_1' \
-    --saved_model_tags=serve
+    --saved_model_tags=serve \
     /mobilenet/saved_model \
@@ -43,2 +42,13 @@ /mobilenet/web_model
 
+Frozen model example:
+
+```bash
+$ tensorflowjs_converter \
+    --input_format=tf_frozen_model \
+    --output_node_names='MobilenetV1/Predictions/Reshape_1' \
+    --saved_model_tags=serve \
+    /mobilenet/frozen_model.pb \
+    /mobilenet/web_model
+```
+
 Session bundle model example:
@@ -54,5 +64,14 @@
 
+Tensorflow Hub module example:
+
+```bash
+$ tensorflowjs_converter \
+    --input_format=tf_hub \
+    'https://tfhub.dev/google/imagenet/mobilenet_v1_100_224/classification/1' \
+    /mobilenet/web_model
+```
+
 |Positional Arguments | Description |
 |---|---|
-|`input_path`  | Full path of the saved model or session bundle directory.|
+|`input_path`  | Full path of the saved model directory, session bundle directory, frozen model file or Tensorflow Hub module handle or path.|
 |`output_dir`  | Path for all output artifacts.|
@@ -63,3 +82,3 @@
 |---|---|
-|`--input_format`     | The format of input model, use tf_saved_model for SavedModel and tf_session_bundle for session bundle. |
+|`--input_format`     | The format of input model, use tf_saved_model for SavedModel, tf_frozen_model for frozen model and tf_session_bundle for session bundle. |
 |`--output_node_names`| The names of the output nodes, separated by commas.|
@@ -204,1 +223,15 @@ |`--saved_model_tags` | Only applicable to SavedModel conversion, Tags of the MetaGraphDef to load, in comma separated format. Defaults to `serve`.|
 ```
+
+To generate the static js file for GraphDef proto, run following steps:
+
+1. Generate static js file with comment first, in order to generate typescript definition.
+```bash
+$ node_modules/protobufjs/bin/pbjs -t static-module -w commonjs -o src/data/compiled_api.js --no-create --no-encode --no-verify --no-convert --no-delimited --no-beautify src/data/api.proto
+
+$ node_modules/protobufjs/bin/pbts -o src/data/compiled_api.d.ts src/data/compiled_api.js
+```
+
+2. Replace the static js file with the version without comments.
+```bash
+$ node_modules/protobufjs/bin/pbjs -t static-module -w commonjs -o src/data/compiled_api.js --no-create --no-encode --no-verify --no-convert --no-delimited --no-beautify --no-comments src/data/api.proto
+```

New alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

New author

Supply chain risk

A new npm collaborator published a version of the package for the first time. New collaborators are usually benign additions to a project, but do indicate a change to the security surface area of a package.

Found 1 instance in 1 package

Fixed alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

New author

Supply chain risk

A new npm collaborator published a version of the package for the first time. New collaborators are usually benign additions to a project, but do indicate a change to the security surface area of a package.

Found 1 instance in 1 package

Improved metrics

Number of lines in readme file

231

increased by16.67%

Worsened metrics

Total package byte prevSize

630047

decreased by-61.25%

Lines of code

14623

decreased by-55.49%

No dependency changes