xxq250
/
mindspore
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

reduce lite code Codespell error number to 0

This commit is contained in:
hukang hwx963878 2021-03-27 16:10:57 +08:00
parent 24634feb63
commit 6fab0900b2
8 changed files with 95 additions and 75 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
model_zoo/official/lite/image_segmentation/app/src/main/java/com/mindspore/imagesegmentation/MainActivity.java
View File

@ -286,7 +286,7 @@ public class MainActivity extends AppCompatActivity implements OnBackgroundImage
progressBar.setVisibility(View.VISIBLE);
new Thread(() -> {
isRunningModel = true;
modelTrackingResult = trackingMobile.execut(originBitmap);
modelTrackingResult = trackingMobile.execute(originBitmap);
if (modelTrackingResult != null) {
isRunningModel = false;
lastOriginBitmap = originBitmap;

10
model_zoo/official/lite/image_segmentation/app/src/main/java/com/mindspore/imagesegmentation/help/TrackingMobile.java
View File

@ -84,19 +84,19 @@ public class TrackingMobile {
}
msConfig.free();
// Complile graph.
// Complie graph.
if (!session.compileGraph(model)) {
Log.e(TAG, "Compile graph failed");
model.freeBuffer();
return;
}
// Note: when use model.freeBuffer(), the model can not be complile graph again.
// Note: when use model.freeBuffer(), the model can not be complie graph again.
model.freeBuffer();
}
public ModelTrackingResult execut(Bitmap bitmap) {
public ModelTrackingResult execute(Bitmap bitmap) {
// Set input tensor values.
List<MSTensor> inputs = session.getInputs();
if (inputs.size() != 1) {
@ -135,8 +135,8 @@ public class TrackingMobile {
int batch = output.getShape()[0];
int channel = output.getShape()[1];
int weight = output.getShape()[2];
int hight = output.getShape()[3];
int plane = weight * hight;
int height = output.getShape()[3];
int plane = weight * height;
for (int n = 0; n < batch; n++) {
for (int c = 0; c < channel; c++) {

4
model_zoo/official/lite/posenet/README.en.md
View File

@ -187,14 +187,14 @@ The inference code process of bone detection demo is as follows. For details abo
- Load the model file and build a computational graph for inference.
```java
// Complile graph.
// Compile graph.
if (!session.compileGraph(model)) {
Log.e("MS_LITE", "Compile graph failed");
model.freeBuffer();
return false;
}
// Note: when use model.freeBuffer(), the model can not be complile graph again.
// Note: when use model.freeBuffer(), the model can not be compile graph again.
model.freeBuffer();
```

4
model_zoo/official/lite/posenet/README.md
View File

@ -190,14 +190,14 @@
- 加载模型文件并构建用于推理的计算图
```java
// Complile graph.
// Compile graph.
if (!session.compileGraph(model)) {
Log.e("MS_LITE", "Compile graph failed");
model.freeBuffer();
return false;
}
// Note: when use model.freeBuffer(), the model can not be complile graph again.
// Note: when use model.freeBuffer(), the model can not be compile graph again.
model.freeBuffer();
```

132
model_zoo/official/lite/posenet/app/src/main/java/com/mindspore/posenetdemo/Posenet.java
View File

@ -115,14 +115,14 @@ public class Posenet {
}
msConfig.free();
// Complile graph.
// Compile graph.
if (!session.compileGraph(model)) {
Log.e("MS_LITE", "Compile graph failed");
model.freeBuffer();
return false;
}
// Note: when use model.freeBuffer(), the model can not be complile graph again.
// Note: when use model.freeBuffer(), the model can not be compile graph again.
model.freeBuffer();
return true;
@ -198,60 +198,12 @@ public class Posenet {
String.format("Interpreter took %.2f ms", 1.0f * lastInferenceTimeNanos / 1_000_000)
);
// Get output tensor values.
List<MSTensor> heatmaps_list = session.getOutputsByNodeName("Conv2D-27");
if (heatmaps_list == null) {
float[][][][] heatmaps = runConv2Dfor27();
float[][][][] offsets = runConv2Dfor28();
if (heatmaps == null || offsets ==null){
return null;
}
MSTensor heatmaps_tensors = heatmaps_list.get(0);
float[] heatmaps_results = heatmaps_tensors.getFloatData();
int[] heatmapsShape = heatmaps_tensors.getShape(); //1, 9, 9 ,17
float[][][][] heatmaps = new float[heatmapsShape[0]][][][];
for (int x = 0; x < heatmapsShape[0]; x++) { // heatmapsShape[0] =1
float[][][] arrayThree = new float[heatmapsShape[1]][][];
for (int y = 0; y < heatmapsShape[1]; y++) { // heatmapsShape[1] = 9
float[][] arrayTwo = new float[heatmapsShape[2]][];
for (int z = 0; z < heatmapsShape[2]; z++) { //heatmapsShape[2] = 9
float[] arrayOne = new float[heatmapsShape[3]]; //heatmapsShape[3] = 17
for (int i = 0; i < heatmapsShape[3]; i++) {
int n = i + z * heatmapsShape[3] + y * heatmapsShape[2] * heatmapsShape[3] + x * heatmapsShape[1] * heatmapsShape[2] * heatmapsShape[3];
arrayOne[i] = heatmaps_results[n]; //1*9*9*17 ??
}
arrayTwo[z] = arrayOne;
}
arrayThree[y] = arrayTwo;
}
heatmaps[x] = arrayThree;
}
List<MSTensor> offsets_list = session.getOutputsByNodeName("Conv2D-28");
if (offsets_list == null) {
return null;
}
MSTensor offsets_tensors = offsets_list.get(0);
float[] offsets_results = offsets_tensors.getFloatData();
int[] offsetsShapes = offsets_tensors.getShape();
float[][][][] offsets = new float[offsetsShapes[0]][][][];
for (int x = 0; x < offsetsShapes[0]; x++) {
float[][][] offsets_arrayThree = new float[offsetsShapes[1]][][];
for (int y = 0; y < offsetsShapes[1]; y++) {
float[][] offsets_arrayTwo = new float[offsetsShapes[2]][];
for (int z = 0; z < offsetsShapes[2]; z++) {
float[] offsets_arrayOne = new float[offsetsShapes[3]];
for (int i = 0; i < offsetsShapes[3]; i++) {
int n = i + z * offsetsShapes[3] + y * offsetsShapes[2] * offsetsShapes[3] + x * offsetsShapes[1] * offsetsShapes[2] * offsetsShapes[3];
offsets_arrayOne[i] = offsets_results[n];
}
offsets_arrayTwo[z] = offsets_arrayOne;
}
offsets_arrayThree[y] = offsets_arrayTwo;
}
offsets[x] = offsets_arrayThree;
}
int height = ((Object[]) heatmaps[0]).length; //9
int width = ((Object[]) heatmaps[0][0]).length; //9
@ -288,8 +240,8 @@ public class Posenet {
int positionY = (int) position.first;
int positionX = (int) position.second;
yCoords[i] = ((float) positionY / (float) (height - 1) * bitmap.getHeight() + offsets[0][positionY][positionX][i]);
xCoords[i] = ((float) positionX / (float) (width - 1) * bitmap.getWidth() + offsets[0][positionY][positionX][i + numKeypoints]);
yCoords[i] = ((float) positionY / (float) (height - 1) * bitmap.getHeight() + offsets[0][positionY][positionX][i]);
xCoords[i] = ((float) positionX / (float) (width - 1) * bitmap.getWidth() + offsets[0][positionY][positionX][i + numKeypoints]);
confidenceScores[i] = sigmoid(heatmaps[0][positionY][positionX][i]);
}
@ -311,4 +263,72 @@ public class Posenet {
return person;
}
private float[][][][] runConv2Dfor27() {
// Get output tensor values.
List<MSTensor> heatmaps_list = session.getOutputsByNodeName("Conv2D-27");
if (heatmaps_list == null) {
return null;
}
MSTensor heatmaps_tensors = heatmaps_list.get(0);
float[] heatmaps_results = heatmaps_tensors.getFloatData();
int[] heatmapsShape = heatmaps_tensors.getShape(); //1, 9, 9 ,17
if (heatmapsShape[0] < 0 || heatmapsShape[1] < 0 || heatmapsShape[2] < 0 || heatmapsShape[3] < 0) {
return null;
}
float[][][][] heatmaps = new float[heatmapsShape[0]][][][];
for (int x = 0; x < heatmapsShape[0]; x++) { // heatmapsShape[0] =1
float[][][] arrayThree = new float[heatmapsShape[1]][][];
for (int y = 0; y < heatmapsShape[1]; y++) { // heatmapsShape[1] = 9
float[][] arrayTwo = new float[heatmapsShape[2]][];
for (int z = 0; z < heatmapsShape[2]; z++) { //heatmapsShape[2] = 9
float[] arrayOne = new float[heatmapsShape[3]]; //heatmapsShape[3] = 17
for (int i = 0; i < heatmapsShape[3]; i++) {
int n = i + z * heatmapsShape[3] + y * heatmapsShape[2] * heatmapsShape[3] + x * heatmapsShape[1] * heatmapsShape[2] * heatmapsShape[3];
arrayOne[i] = heatmaps_results[n]; //1*9*9*17 ??
}
arrayTwo[z] = arrayOne;
}
arrayThree[y] = arrayTwo;
}
heatmaps[x] = arrayThree;
}
return heatmaps;
}
private float[][][][] runConv2Dfor28() {
List<MSTensor> offsets_list = session.getOutputsByNodeName("Conv2D-28");
if (offsets_list == null) {
return null;
}
MSTensor offsets_tensors = offsets_list.get(0);
float[] offsets_results = offsets_tensors.getFloatData();
int[] offsetsShapes = offsets_tensors.getShape();
if (offsetsShapes[0] < 0 || offsetsShapes[1] < 0 || offsetsShapes[2] < 0 || offsetsShapes[3] < 0) {
return null;
}
float[][][][] offsets = new float[offsetsShapes[0]][][][];
for (int x = 0; x < offsetsShapes[0]; x++) {
float[][][] offsets_arrayThree = new float[offsetsShapes[1]][][];
for (int y = 0; y < offsetsShapes[1]; y++) {
float[][] offsets_arrayTwo = new float[offsetsShapes[2]][];
for (int z = 0; z < offsetsShapes[2]; z++) {
float[] offsets_arrayOne = new float[offsetsShapes[3]];
for (int i = 0; i < offsetsShapes[3]; i++) {
int n = i + z * offsetsShapes[3] + y * offsetsShapes[2] * offsetsShapes[3] + x * offsetsShapes[1] * offsetsShapes[2] * offsetsShapes[3];
offsets_arrayOne[i] = offsets_results[n];
}
offsets_arrayTwo[z] = offsets_arrayOne;
}
offsets_arrayThree[y] = offsets_arrayTwo;
}
offsets[x] = offsets_arrayThree;
}
return offsets;
}
}

6
model_zoo/official/lite/style_transfer/README.en.md
View File

@ -154,7 +154,7 @@ The inference code process of style transfer demo is as follows. For details abo
- Load the model file and build a computational graph for inference.
```java
// Complile graph.
// Compile graph.
if (!Predict_session.compileGraph(style_predict_model)) {
Log.e("MS_LITE", "Compile style_predict graph failed");
style_predict_model.freeBuffer();
@ -164,7 +164,7 @@ The inference code process of style transfer demo is as follows. For details abo
style_transform_model.freeBuffer();
}
// Note: when use model.freeBuffer(), the model can not be complile graph again.
// Note: when use model.freeBuffer(), the model can not be compile graph again.
style_predict_model.freeBuffer();
style_transform_model.freeBuffer();
```
@ -223,7 +223,7 @@ The inference code process of style transfer demo is as follows. For details abo
// Get output tensor values.
List<String> tensorNames = Predict_session.getOutputTensorNames();
Map<String, MSTensor> outputs = Predict_session.getOutputMapByTensor();
Set<Map.Entry<String, MSTensor>> entrys = outputs.entrySet();
Set<Map.Entry<String, MSTensor>> entry = outputs.entrySet();
float[] Predict_results = null;
for (String tensorName : tensorNames) {

6
model_zoo/official/lite/style_transfer/README.md
View File

@ -157,7 +157,7 @@
- 加载模型文件并构建用于推理的计算图
```java
// Complile graph.
// Compile graph.
if (!Predict_session.compileGraph(style_predict_model)) {
Log.e("MS_LITE", "Compile style_predict graph failed");
style_predict_model.freeBuffer();
@ -167,7 +167,7 @@
style_transform_model.freeBuffer();
}
// Note: when use model.freeBuffer(), the model can not be complile graph again.
// Note: when use model.freeBuffer(), the model can not be compile graph again.
style_predict_model.freeBuffer();
style_transform_model.freeBuffer();
```
@ -225,7 +225,7 @@
// Get output tensor values.
List<String> tensorNames = Predict_session.getOutputTensorNames();
Map<String, MSTensor> outputs = Predict_session.getOutputMapByTensor();
Set<Map.Entry<String, MSTensor>> entrys = outputs.entrySet();
Set<Map.Entry<String, MSTensor>> entry = outputs.entrySet();
float[] Predict_results = null;
for (String tensorName : tensorNames) {

6
model_zoo/official/lite/style_transfer/app/src/main/java/com/mindspore/styletransferdemo/StyleTransferModelExecutor.java
View File

@ -96,7 +96,7 @@ public class StyleTransferModelExecutor {
msConfig.free();
// Complile graph.
// Compile graph.
if (!Predict_session.compileGraph(style_predict_model)) {
Log.e("MS_LITE", "Compile style_predict graph failed");
style_predict_model.freeBuffer();
@ -106,7 +106,7 @@ public class StyleTransferModelExecutor {
style_transform_model.freeBuffer();
}
// Note: when use model.freeBuffer(), the model can not be complile graph again.
// Note: when use model.freeBuffer(), the model can not be compile graph again.
style_predict_model.freeBuffer();
style_transform_model.freeBuffer();
}
@ -165,7 +165,7 @@ public class StyleTransferModelExecutor {
// Get output tensor values.
List<String> tensorNames = Predict_session.getOutputTensorNames();
Map<String, MSTensor> outputs = Predict_session.getOutputMapByTensor();
Set<Map.Entry<String, MSTensor>> entrys = outputs.entrySet();
Set<Map.Entry<String, MSTensor>> entry = outputs.entrySet();
float[] Predict_results = null;
for (String tensorName : tensorNames) {