model_dsm_msr.py

# -*- coding: utf-8 -*-
"""DMI_MSR.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/1wa0-XtJpB5E6CA_p0abh8Y7Dqz9U_Vnd
"""

from google.colab import drive
drive.mount('/content/drive')

import numpy as np
import matplotlib.pyplot as plt
import os
from random import shuffle
from tqdm import tqdm
import cv2

def get_data(DATADIR):
  CATEGORIES = ["a01", "a02", "a03", "a04", "a05", "a06", "a07", "a08", "a09", "a10", "a11", "a12", "a13", "a14", "a15", "a16", "a17", "a18", "a19", "a20"]

  for img in os.listdir(DATADIR):
    img_array = cv2.imread(os.path.join(DATADIR, img), cv2.IMREAD_COLOR)
    plt.imshow(img_array)
    plt.show()
    break

  IMG_SIZE = 112

  new_array = cv2.resize(img_array, (IMG_SIZE, IMG_SIZE))
  plt.imshow(new_array, cmap = 'gray')
  plt.show()
  # a01_s01_e01
  def action_label_img(img):
    action_label = img.split('_')[-4]
    if action_label[1] == '0':
      i = int(action_label[2:]) - 1
      label = [0] * 20
      label[i] = 1
      return label
    else:
      i = int(action_label[1:]) - 1
      label = [0] * 20
      label[i] = 1
      return label

  training_data = []

  def create_training_data():
    for img in tqdm(os.listdir(DATADIR)):
      try:
        img_array = cv2.imread(os.path.join(DATADIR, img), cv2.IMREAD_GRAYSCALE)
        new_array = cv2.resize(img_array, (IMG_SIZE, IMG_SIZE))
        #category = img.split('_')[-4]
        #class_num = CATEGORIES.index(category)
        class_num = action_label_img(img)
        training_data.append([new_array, class_num])
      except Exception as e:
        pass
    shuffle(training_data)
    # np.save('train_data.npy', training_data)
  create_training_data()
  X = []
  Y = []

  for features, label in training_data:
    X.append(features)
    Y.append(label)
  
  X = np.array(X).reshape(-1, IMG_SIZE, IMG_SIZE, 1)
  Y = np.array(Y)
  return X,Y

X_train,y_train = get_data("/content/drive/My Drive/Minor Project/DMI_MSR/subject_odd")

print(X_train.shape,y_train.shape)

X_test,y_test = get_data("/content/drive/My Drive/Minor Project/DMI_MSR/subject_even")

print(X_test.shape,y_test.shape)

import keras
from keras.callbacks import ModelCheckpoint, EarlyStopping
import tensorflow as tf
from tensorflow.keras.models import Sequential
from sklearn.model_selection import KFold
from tensorflow.keras.layers import Dense, Dropout, Activation, Flatten, Conv2D, MaxPooling2D
from sklearn.model_selection import train_test_split
from keras.regularizers import l1, l2, l1_l2

model = Sequential()

model.add(Conv2D(32, (7, 7), input_shape=X_train.shape[1:], activation = 'relu',kernel_regularizer = l1(0.0001)))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(64, (5, 5),activation = 'relu',kernel_regularizer = l1(0.001)))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(128, (3, 3),activation = 'relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(256, (3, 3),activation = 'relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(512, (2, 2),activation = 'relu', kernel_regularizer = l2(0.1)))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Flatten())
model.add(Dropout(0.3))
model.add(Dense(128))
model.add(Activation('relu'))

model.add(Dropout(0.2))
model.add(Dense(20))
model.add(Activation('softmax'))

opt = keras.optimizers.Adam(learning_rate=0.0001)
model.compile(loss="categorical_crossentropy", optimizer=opt, metrics=["accuracy"])

earlystopper = EarlyStopping(monitor='val_loss', min_delta=0, patience=15, verbose=1, mode='auto', baseline=None, restore_best_weights=False)
# checkpoint = ModelCheckpoint(filepath='/checkpoint/checkpoint-{epoch:02d}-{val_loss:.2f}-{val_accuracy}.hdf5')

filepath='/content/checkpoint/checkpoint-{val_accuracy:.4f}-{val_loss:.2f}-{epoch:02d}.hdf5'
checkpoint = ModelCheckpoint(filepath, monitor='val_accuracy', verbose=1, save_best_only=True, mode='max')

# clear checkpoint folder
folder = '/content/checkpoint/'
for filename in os.listdir(folder):
    file_path = os.path.join(folder, filename)
    try:
        if os.path.isfile(file_path) or os.path.islink(file_path):
            os.unlink(file_path)
        elif os.path.isdir(file_path):
            shutil.rmtree(file_path)
    except Exception as e:
        print('Failed to delete %s. Reason: %s' % (file_path, e))

history = model.fit(X_train, y_train, epochs=2000, batch_size=64, validation_data=(X_test, y_test), verbose=1,callbacks=[checkpoint])

# get model with best val accuracy
import glob
list_of_files = glob.glob('/content/checkpoint/*') 
latest_file = max(list_of_files, key=os.path.getctime)
print(latest_file)

print("Model Evaluate...")
new_model = tf.keras.models.load_model(latest_file)
loss, accuracy = new_model.evaluate(X_test,y_test)
# loss, accuracy = model.evaluate(X_test,y_test)
print("loss: ",loss)
print("Tesing Accuracy: ", accuracy)

plt.plot(history.history['accuracy'][:1000])
plt.plot(history.history['val_accuracy'][:1000])
plt.title('model accuracy')
plt.ylabel('acuuracy')
plt.xlabel('epoch')
plt.legend(['train','test'], loc='upper left')
plt.show()
plt.plot(history.history['loss'][:1000])
plt.plot(history.history['val_loss'][:1000])
plt.title('model loss')
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['train','test'], loc='upper right')
plt.show()

import pandas as pd

history.history['val_loss']

hist_df = pd.DataFrame(history.history) 

# save to json:  
#hist_json_file = 'history.json' 
#with open(hist_json_file, mode='w') as f:
#   hist_df.to_json(f)

# or save to csv: 
hist_csv_file = 'history.csv'
with open(hist_csv_file, mode='w') as f:
    hist_df.to_csv(f)

dot_img_file = 'model_1.png'
tf.keras.utils.plot_model(model, to_file=dot_img_file, show_shapes=True)

y_pred = model.predict(X_test)
matrix = tf.math.confusion_matrix(y_test.argmax(axis=1), y_pred.argmax(axis=1))

labels = ['High-arm-wave',
          'Horizontal-arm-wave',
          'Hammer',
          'Hand-catch',
          'Forward-punch',
          'High-throw',
          'Draw-x',
          'Draw-tick',
          'Draw-circle',
          'Hand-clap',
          'Two-hand-wave',
          'Side-boxing',
          'Bend',
          'Forward-kick',
          'Side-kick',
          'Jogging',
          'Tennis-swing',
          'Tennis-serve',
          'Golf-swing',
          'Pick-up-and-throw']

def plot(cm):
  plt.imshow(cm,interpolation = 'nearest', cmap = plt.cm.Blues)
  plt.title("Confusion Matrix for MSRAction3D Dataset")
  plt.colorbar(fraction=0.0455)
  tick_marks = np.arange(len(labels))
  plt.xticks(tick_marks, labels, rotation = 90)
  plt.yticks(tick_marks, labels)

matrix_norm = np.asarray(matrix)
matrix_norm = matrix_norm.astype('float') / matrix_norm.sum(axis = 1)
plt.figure(figsize=(10,10))
plot(matrix_norm)
plt.savefig('cm.png')