[Kaggle] Digit Recognizer 手写数字识别（卷积神经网络）

from keras import backend as K # 兼容不同后端的代码
from keras.models import Sequential
from keras.layers.convolutional import Conv2D
from keras.layers.convolutional import MaxPooling2D
from keras.layers.core import Activation
from keras.layers.core import Dense
from keras.layers.core import Flatten
from keras.utils import np_utils
from keras.optimizers import SGD, Adam, RMSprop

import numpy as np
%matplotlib inline
import matplotlib.pyplot as plt
import pandas as pd

# 图片格式问题
# K.image_data_format() == 'channels_last' 
# 默认是last是通道  K.set_image_dim_ordering("tf")
# K.image_data_format() == 'channels_first' #  K.set_image_dim_ordering("th")

class LeNet:
    @staticmethod
    def build(input_shape, classes):
        model = Sequential()
        model.add(Conv2D(20,kernel_size=5,padding='same',
                         input_shape=input_shape,activation='relu'))
        model.add(MaxPooling2D(pool_size=(2,2),strides=(2,2)))

        model.add(Conv2D(50,kernel_size=5,padding='same',activation='relu'))
        model.add(MaxPooling2D(pool_size=(2,2),strides=(2,2)))

        model.add(Flatten())
        model.add(Dense(500, activation='relu'))

        model.add(Dense(classes,activation='softmax'))
        return model

train = pd.read_csv('train.csv')
y_train_full = train['label']
X_train_full = train.drop(['label'], axis=1)
X_test_full = pd.read_csv('test.csv')

X_train_full.shape

(42000, 784)

X_train = np.array(X_train_full).reshape(-1,28,28) / 255.0
X_test = np.array(X_test_full).reshape(-1,28,28)/255.0
y_train = np_utils.to_categorical(y_train_full, 10) # 转成oh编码

X_train = X_train[:, :, :, np.newaxis]
# m,28,28 -->  m, 28, 28, 1(单通道)
X_test = X_test[:, :, :, np.newaxis]

model = LeNet.build(input_shape=(28, 28, 1), classes=10)

opt = Adam(learning_rate=0.001, beta_1=0.9, beta_2=0.999, decay=0.01)
model.compile(loss="categorical_crossentropy",
              optimizer=opt, metrics=["accuracy"])

history = model.fit(X_train, y_train, epochs=20, batch_size=128,
                    validation_split=0.2)

Epoch 1/20
263/263 [==============================] - 26s 98ms/step - 
loss: 0.2554 - accuracy: 0.9235 - 
val_loss: 0.0983 - val_accuracy: 0.9699
Epoch 2/20
263/263 [==============================] - 27s 103ms/step - 
loss: 0.0806 - accuracy: 0.9761 - 
val_loss: 0.0664 - val_accuracy: 0.9787
...
...
Epoch 20/20
263/263 [==============================] - 25s 97ms/step - 
loss: 0.0182 - accuracy: 0.9953 - 
val_loss: 0.0405 - val_accuracy: 0.9868

model.summary()

Model: "sequential"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d (Conv2D)              (None, 28, 28, 20)        520       
_________________________________________________________________
max_pooling2d (MaxPooling2D) (None, 14, 14, 20)        0         
_________________________________________________________________
conv2d_1 (Conv2D)            (None, 14, 14, 50)        25050     
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 7, 7, 50)          0         
_________________________________________________________________
flatten (Flatten)            (None, 2450)              0         
_________________________________________________________________
dense (Dense)                (None, 500)               1225500   
_________________________________________________________________
dense_1 (Dense)              (None, 10)                5010      
=================================================================
Total params: 1,256,080
Trainable params: 1,256,080
Non-trainable params: 0
_________________________________________________________________

from keras.utils import plot_model
plot_model(model, './model.png', show_shapes=True)

pd.DataFrame(history.history).plot(figsize=(8, 5))
plt.grid(True)
plt.gca().set_ylim(0, 1) # set the vertical range to [0-1]
plt.show()

y_pred = model.predict(X_test)
pred = y_pred.argmax(axis=1).reshape(-1)
print(pred.shape)

image_id = pd.Series(range(1,len(pred)+1))
output = pd.DataFrame({'ImageId':image_id, 'Label':pred})
output.to_csv("submission_NN.csv",  index=False)

Help on function VGG16 in module tensorflow.python.keras.applications.vgg16:

VGG16(include_top=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000, classifier_activation='softmax')
    Instantiates the VGG16 model.
    
    Reference paper:
    - [Very Deep Convolutional Networks for Large-Scale Image Recognition](
    https://arxiv.org/abs/1409.1556) (ICLR 2015)
    
    By default, it loads weights pre-trained on ImageNet. Check 'weights' for
    other options.
    
    This model can be built both with 'channels_first' data format
    (channels, height, width) or 'channels_last' data format
    (height, width, channels).
    
    The default input size for this model is 224x224.
    
    Caution: Be sure to properly pre-process your inputs to the application.
    Please see `applications.vgg16.preprocess_input` for an example.
    
    Arguments:
        include_top: whether to include the 3 fully-connected
            layers at the top of the network.
        weights: one of `None` (random initialization),
              'imagenet' (pre-training on ImageNet),
              or the path to the weights file to be loaded.
        input_tensor: optional Keras tensor
            (i.e. output of `layers.Input()`)
            to use as image input for the model.
        input_shape: optional shape tuple, only to be specified
            if `include_top` is False (otherwise the input shape
            has to be `(224, 224, 3)`
            (with `channels_last` data format)
            or `(3, 224, 224)` (with `channels_first` data format).
            It should have exactly 3 input channels,
            and width and height should be no smaller than 32.
            E.g. `(200, 200, 3)` would be one valid value.
        pooling: Optional pooling mode for feature extraction
            when `include_top` is `False`.
            - `None` means that the output of the model will be
                the 4D tensor output of the
                last convolutional block.
            - `avg` means that global average pooling
                will be applied to the output of the
                last convolutional block, and thus
                the output of the model will be a 2D tensor.
            - `max` means that global max pooling will
                be applied.
        classes: optional number of classes to classify images
            into, only to be specified if `include_top` is True, and
            if no `weights` argument is specified.
        classifier_activation: A `str` or callable. The activation function to use
            on the "top" layer. Ignored unless `include_top=True`. Set
            `classifier_activation=None` to return the logits of the "top" layer.
    
    Returns:
      A `keras.Model` instance.
    
    Raises:
      ValueError: in case of invalid argument for `weights`,
        or invalid input shape.
      ValueError: if `classifier_activation` is not `softmax` or `None` when
        using a pretrained top layer.

import numpy as np
%matplotlib inline
import matplotlib.pyplot as plt
import pandas as pd
import cv2
from keras.optimizers import Adam
from keras.models import Model
from keras.utils import np_utils
from keras.models import Sequential
from keras.layers import Flatten
from keras.layers import Dense
from keras.layers import Input
from keras.layers import Dropout
from keras.applications.vgg16 import VGG16

vgg16 = VGG16(weights='imagenet',include_top=False,
              input_shape=(32, 32, 3))
# VGG16 模型在include_top=False时，可以自定义输入大小，至少32x32，通道必须是3

mylayer = vgg16.output
mylayer = Flatten()(mylayer)
mylayer = Dense(128, activation='relu')(mylayer)
mylayer = Dropout(0.3)(mylayer)
mylayer = Dense(10, activation='softmax')(mylayer)

model = Model(inputs=vgg16.inputs, outputs=mylayer)

for layer in vgg16.layers:
    layer.trainable = False # vgg16的各个层不训练

train = pd.read_csv('train.csv')
y_train_full = train['label']
X_train_full = train.drop(['label'], axis=1)
X_test_full = pd.read_csv('test.csv')

def process(data):
    data = np.array(data).reshape(-1,28,28)
    output = np.zeros((data.shape[0], 32, 32, 3))
    for i in range(data.shape[0]):
        img = data[i]
        rgb_array = np.zeros((img.shape[0], img.shape[1], 3), "uint8")
        rgb_array[:, :, 0], rgb_array[:, :, 1], rgb_array[:, :, 2] = img, img, img
        pic = cv2.resize(rgb_array, (32, 32), interpolation=cv2.INTER_LINEAR)
        output[i] = pic
    output = output.astype('float32')/255.0
    return output

y_train = np_utils.to_categorical(y_train_full, 10)
X_train = process(X_train_full)
X_test = process(X_test_full)

print(X_train.shape)
print(X_test.shape)

(42000, 32, 32, 3)
(28000, 32, 32, 3)

img = X_train[0]
plt.imshow(img)
np.set_printoptions(threshold=np.inf)# 全部显示矩阵
# print(X_train[0])

opt = Adam(learning_rate=0.001, beta_1=0.9, beta_2=0.999, decay=0.01)
model.compile(loss="categorical_crossentropy",
              optimizer=opt, metrics=["accuracy"])

history = model.fit(X_train, y_train, epochs=50, batch_size=128,
                    validation_split=0.2)

Epoch 1/50
263/263 [==============================] - 101s 384ms/step - 
loss: 0.9543 - accuracy: 0.7212 - 
val_loss: 0.5429 - val_accuracy: 0.8601
...
Epoch 10/50
263/263 [==============================] - 110s 417ms/step - 
loss: 0.3284 - accuracy: 0.9063 - 
val_loss: 0.2698 - val_accuracy: 0.9263
...
Epoch 40/50
263/263 [==============================] - 114s 433ms/step - 
loss: 0.2556 - accuracy: 0.9254 - 
val_loss: 0.2121 - val_accuracy: 0.9389
...
Epoch 50/50
263/263 [==============================] - 110s 420ms/step - 
loss: 0.2466 - accuracy: 0.9272 - 
val_loss: 0.2058 - val_accuracy: 0.9406

model.summary()

Model: "functional_15"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_23 (InputLayer)        [(None, 32, 32, 3)]       0         
_________________________________________________________________
block1_conv1 (Conv2D)        (None, 32, 32, 64)        1792      
_________________________________________________________________
block1_conv2 (Conv2D)        (None, 32, 32, 64)        36928     
_________________________________________________________________
block1_pool (MaxPooling2D)   (None, 16, 16, 64)        0         
_________________________________________________________________
block2_conv1 (Conv2D)        (None, 16, 16, 128)       73856     
_________________________________________________________________
block2_conv2 (Conv2D)        (None, 16, 16, 128)       147584    
_________________________________________________________________
block2_pool (MaxPooling2D)   (None, 8, 8, 128)         0         
_________________________________________________________________
block3_conv1 (Conv2D)        (None, 8, 8, 256)         295168    
_________________________________________________________________
block3_conv2 (Conv2D)        (None, 8, 8, 256)         590080    
_________________________________________________________________
block3_conv3 (Conv2D)        (None, 8, 8, 256)         590080    
_________________________________________________________________
block3_pool (MaxPooling2D)   (None, 4, 4, 256)         0         
_________________________________________________________________
block4_conv1 (Conv2D)        (None, 4, 4, 512)         1180160   
_________________________________________________________________
block4_conv2 (Conv2D)        (None, 4, 4, 512)         2359808   
_________________________________________________________________
block4_conv3 (Conv2D)        (None, 4, 4, 512)         2359808   
_________________________________________________________________
block4_pool (MaxPooling2D)   (None, 2, 2, 512)         0         
_________________________________________________________________
block5_conv1 (Conv2D)        (None, 2, 2, 512)         2359808   
_________________________________________________________________
block5_conv2 (Conv2D)        (None, 2, 2, 512)         2359808   
_________________________________________________________________
block5_conv3 (Conv2D)        (None, 2, 2, 512)         2359808   
_________________________________________________________________
block5_pool (MaxPooling2D)   (None, 1, 1, 512)         0         
_________________________________________________________________
flatten_19 (Flatten)         (None, 512)               0         
_________________________________________________________________
dense_28 (Dense)             (None, 128)               65664     
_________________________________________________________________
dropout_9 (Dropout)          (None, 128)               0         
_________________________________________________________________
dense_29 (Dense)             (None, 10)                1290      
=================================================================
Total params: 14,781,642
Trainable params: 66,954
Non-trainable params: 14,714,688
_________________________________________________________________

from keras.utils import plot_model
plot_model(model, './model.png', show_shapes=True)

y_pred = model.predict(X_test)
pred = y_pred.argmax(axis=1).reshape(-1)
print(pred.shape)
print(pred)

image_id = pd.Series(range(1,len(pred)+1))
output = pd.DataFrame({'ImageId':image_id, 'Label':pred})
output.to_csv("submission_NN.csv",  index=False)