{"cells":[{"cell_type":"markdown","metadata":{"_cell_guid":"7daa5a37-ea6b-2274-4bc1-fadb0a2fc41a"},"source":"# Use keras to classify Sea Lions\n\n- I am using the first picture to extract Sea Lion coordinates using blob detection\n- I extract 64 by 64 images centered on the extracted coordinates\n- I train a simple keras model\n\n*** The test accuracy is for Sea Lions in the first image only and without negative examples** "},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"35cabbd8-8e7b-5be7-bd00-61b1addc2d75"},"outputs":[],"source":"import numpy as np\nimport pandas as pd\nimport os\nimport cv2\nimport matplotlib.pyplot as plt\nimport skimage.feature\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.preprocessing import LabelBinarizer\nimport keras\nfrom keras.models import Sequential, load_model\nfrom keras.layers import Dense, Dropout, Activation, Flatten, Conv2D, MaxPooling2D, Lambda, Cropping2D\nfrom keras.utils import np_utils\n%matplotlib inline"},{"cell_type":"markdown","metadata":{"_cell_guid":"39c70a8d-7645-f2f2-8e09-7d528eb48e57"},"source":"### Initialize variables"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"3a6329c7-aa3b-b576-b6e1-d675e6e8fbf2"},"outputs":[],"source":"classes = [\"adult_males\", \"subadult_males\", \"adult_females\", \"juveniles\", \"pups\"]\n\nfile_names = os.listdir(\"../input/Train/\")\nfile_names = sorted(file_names, key=lambda \n                    item: (int(item.partition('.')[0]) if item[0].isdigit() else float('inf'), item)) \n\n# select a subset of files to run on\nfile_names = file_names[0:1]\n\n# dataframe to store results in\ncoordinates_df = pd.DataFrame(index=file_names, columns=classes)"},{"cell_type":"markdown","metadata":{"_cell_guid":"f6aecb87-1c65-5c28-12c8-d86c42ae223b"},"source":"### Extract coordinates"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"7755c681-04df-368a-aca2-f099dd9ce805"},"outputs":[],"source":"for filename in file_names:\n    \n    # read the Train and Train Dotted images\n    image_1 = cv2.imread(\"../input/TrainDotted/\" + filename)\n    image_2 = cv2.imread(\"../input/Train/\" + filename)\n    \n    # absolute difference between Train and Train Dotted\n    image_3 = cv2.absdiff(image_1,image_2)\n    \n    # mask out blackened regions from Train Dotted\n    mask_1 = cv2.cvtColor(image_1, cv2.COLOR_BGR2GRAY)\n    mask_1[mask_1 < 20] = 0\n    mask_1[mask_1 > 0] = 255\n    \n    mask_2 = cv2.cvtColor(image_2, cv2.COLOR_BGR2GRAY)\n    mask_2[mask_2 < 20] = 0\n    mask_2[mask_2 > 0] = 255\n    \n    image_3 = cv2.bitwise_or(image_3, image_3, mask=mask_1)\n    image_3 = cv2.bitwise_or(image_3, image_3, mask=mask_2) \n    \n    # convert to grayscale to be accepted by skimage.feature.blob_log\n    image_3 = cv2.cvtColor(image_3, cv2.COLOR_BGR2GRAY)\n    \n    # detect blobs\n    blobs = skimage.feature.blob_log(image_3, min_sigma=3, max_sigma=4, num_sigma=1, threshold=0.02)\n    \n    adult_males = []\n    subadult_males = []\n    pups = []\n    juveniles = []\n    adult_females = [] \n    \n    for blob in blobs:\n        # get the coordinates for each blob\n        y, x, s = blob\n        # get the color of the pixel from Train Dotted in the center of the blob\n        g,b,r = image_1[int(y)][int(x)][:]\n        \n        # decision tree to pick the class of the blob by looking at the color in Train Dotted\n        if r > 200 and g < 50 and b < 50: # RED\n            adult_males.append((int(x),int(y)))        \n        elif r > 200 and g > 200 and b < 50: # MAGENTA\n            subadult_males.append((int(x),int(y)))         \n        elif r < 100 and g < 100 and 150 < b < 200: # GREEN\n            pups.append((int(x),int(y)))\n        elif r < 100 and  100 < g and b < 100: # BLUE\n            juveniles.append((int(x),int(y))) \n        elif r < 150 and g < 50 and b < 100:  # BROWN\n            adult_females.append((int(x),int(y)))\n            \n    coordinates_df[\"adult_males\"][filename] = adult_males\n    coordinates_df[\"subadult_males\"][filename] = subadult_males\n    coordinates_df[\"adult_females\"][filename] = adult_females\n    coordinates_df[\"juveniles\"][filename] = juveniles\n    coordinates_df[\"pups\"][filename] = pups"},{"cell_type":"markdown","metadata":{"_cell_guid":"d03424c1-b12b-ae53-2fed-1dff86398164"},"source":"### Extract 64by 64 images"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"c9549615-3a64-2ef2-2be0-1946e07c2ee2"},"outputs":[],"source":"x = []\ny = []\n\nfor filename in file_names:    \n    image = cv2.imread(\"../input/Train/\" + filename)\n    for lion_class in classes:\n        for coordinates in coordinates_df[lion_class][filename]:\n            thumb = image[coordinates[1]-32:coordinates[1]+32,coordinates[0]-32:coordinates[0]+32,:]\n            if np.shape(thumb) == (64, 64, 3):\n                x.append(thumb)\n                y.append(lion_class)\nx = np.array(x)\ny = np.array(y)"},{"cell_type":"markdown","metadata":{"_cell_guid":"75016379-58d6-1ff4-d411-71bb29eec895"},"source":"### Plot examples"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"981bcb37-d353-dcd1-fc99-ff178605811c"},"outputs":[],"source":"for lion_class in classes:\n    f, ax = plt.subplots(1,10,figsize=(12,1.5))\n    f.suptitle(lion_class)\n    axes = ax.flatten()\n    j = 0\n    for a in axes:\n        a.set_xticks([])\n        a.set_yticks([])\n        for i in range(j,len(x)):\n            if y[i] == lion_class:\n                j = i+1\n                a.imshow(cv2.cvtColor(x[i], cv2.COLOR_BGR2RGB))\n                break"},{"cell_type":"markdown","metadata":{"_cell_guid":"3ae5856f-c680-e4e3-459a-fa764559938a"},"source":"### One hot encoding"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"c1438c4d-e0d4-812a-adff-6f5db4c32a81"},"outputs":[],"source":"encoder = LabelBinarizer()\nencoder.fit(y)\ny = encoder.transform(y).astype(float)"},{"cell_type":"markdown","metadata":{"_cell_guid":"7c0dfde1-a1b3-a181-bcaa-58455025138a"},"source":"### Build Keras model"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"25ecbbe7-cae5-a6fa-3ab0-943fe10f580a"},"outputs":[],"source":"model = Sequential()\n\nmodel.add(Lambda(lambda x: (x / 255.0) - 0.5, input_shape=(64,64,3)))\n\n\nmodel.add(Conv2D(32, (5, 5), activation='relu', padding='same'))\nmodel.add(MaxPooling2D(pool_size=(2,2)))\nmodel.add(Conv2D(64, (5, 5), activation='relu', padding='same'))\n\nmodel.add(Flatten())\n\nmodel.add(Dense(512, activation='relu'))\nmodel.add(Dropout(0.5))\nmodel.add(Dense(5, activation='softmax'))\n\nmodel.compile(loss='categorical_crossentropy',optimizer='adam',metrics=['accuracy'])"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"e9447e9b-92f7-aab7-bd03-03a3aa82b816"},"outputs":[],"source":"history = model.fit(x, y, epochs=20, validation_split=0.2, verbose=0)"},{"cell_type":"markdown","metadata":{"_cell_guid":"bf15c0bf-f00a-f80c-8520-43ef450feedb"},"source":"### Results"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"5782174e-3d6f-c3ce-be48-d8095a07c35e"},"outputs":[],"source":"# http://machinelearningmastery.com/display-deep-learning-model-training-history-in-keras/\n# summarize history for accuracy\nplt.plot(history.history['acc'])\nplt.plot(history.history['val_acc'])\nplt.title('model accuracy')\nplt.ylabel('accuracy')\nplt.xlabel('epoch')\nplt.legend(['train', 'test'], loc='upper left')\nplt.show()\n# summarize history for loss\nplt.plot(history.history['loss'])\nplt.plot(history.history['val_loss'])\nplt.title('model loss')\nplt.ylabel('loss')\nplt.xlabel('epoch')\nplt.legend(['train', 'test'], loc='upper left')\nplt.show()"}],"metadata":{"_change_revision":0,"_is_fork":false,"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.6.0"}},"nbformat":4,"nbformat_minor":0}