# Pose-clf

**Repository Path**: hyd-435/Pose-clf

## Basic Information

- **Project Name**: Pose-clf
- **Description**: Simple Keras project for pose classification using Depth Images
- **Primary Language**: Python
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2018-03-09
- **Last Updated**: 2020-12-19

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# Pose-clf
## Simple Keras project for pose classification using Depth Images

# 数据情况统计

## 样本数据

* #### 标记
![sample-annotations](data/sample-anno.png)


## 标签分布

### 标签 [sitting, standing, lying]

* #### video-1
![video-1](data/video-1.png)

* #### video-2
![video-2](data/video-2.png)

* #### 总共
![video-all](data/all.png)

### 分类器CNN
```
def build_cnn(img_cols, img_rows, nb_class=3, nb_channel=1):
    input_shape = (img_cols, img_rows, nb_channel)
    model = Sequential()
    model.add(Conv2D(32, kernel_size=(3, 3),
                     activation='relu',
                     input_shape=input_shape))
    model.add(Conv2D(64, (3, 3), activation='relu'))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Dropout(0.25))
    model.add(Flatten())
    model.add(Dense(128, activation='relu'))
    model.add(Dropout(0.5))
    model.add(Dense(nb_class, activation='softmax'))

    model.compile(loss="categorical_crossentropy",
                  optimizer="Adam",
                  metrics=['accuracy'])
    return model
```

### 训练结果
```
epochs = 10
batch_size = 32
img_rows, img_cols = 56, 56
train : test = 7 : 3

training loss = 0.005
training accuracy = 0.999
testing loss = 0.959
testing accuracy = 0.824

```