Datasets
Models
Downloads: 1
1241 lines (1240 with data), 265.7 kB
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Using TensorFlow backend.\n"
]
}
],
"source": [
"import os\n",
"import pickle\n",
"import random\n",
"import glob\n",
"import datetime\n",
"import pandas as pd\n",
"import numpy as np\n",
"import cv2\n",
"import pydicom\n",
"from tqdm import tqdm\n",
"from joblib import delayed, Parallel\n",
"import zipfile\n",
"from pydicom.filebase import DicomBytesIO\n",
"import sys\n",
"from PIL import Image\n",
"import cv2\n",
"#from focal_loss import sparse_categorical_focal_loss\n",
"import keras\n",
"#import tensorflow_addons as tfa\n",
"from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
"from keras.models import model_from_json\n",
"import tensorflow as tf\n",
"import keras\n",
"from keras.models import Sequential, Model\n",
"from keras.layers import Dense, Conv2D, Flatten, MaxPooling2D, GlobalAveragePooling2D, Dropout\n",
"from keras.applications.inception_v3 import InceptionV3\n",
"\n",
"# importing pyplot and image from matplotlib \n",
"import matplotlib.pyplot as plt \n",
"import matplotlib.image as mpimg \n",
"from keras.optimizers import SGD\n",
"from keras import backend\n",
"from keras.models import load_model\n",
"\n",
"from keras.preprocessing import image\n",
"import albumentations as A\n",
"\n",
"\n",
"from sklearn.metrics import classification_report, confusion_matrix, roc_auc_score, roc_curve\n",
"import tensorflow as tf"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"from tensorflow.keras.losses import Reduction\n",
"\n",
"from tensorflow_addons.losses import SigmoidFocalCrossEntropy"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"base_url = '/home/ubuntu/kaggle/rsna-intracranial-hemorrhage-detection/'\n",
"TRAIN_DIR = '/home/ubuntu/kaggle/rsna-intracranial-hemorrhage-detection/stage_2_train/'\n",
"TEST_DIR = '/home/ubuntu/kaggle/rsna-intracranial-hemorrhage-detection/stage_2_test/'\n",
"image_dir = '/home/ubuntu/kaggle/rsna-intracranial-hemorrhage-detection/png/train/adjacent-brain-cropped/'\n",
"save_dir = 'home/ubuntu/kaggle/models/'\n",
"os.listdir(base_url)\n",
"\n",
"def png(image): \n",
" return image + '.png'"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# learning rate"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"initial_learning_rate = 1e-2\n",
"first_decay_steps = 1000\n",
"lr_decayed_fn = (\n",
" tf.keras.experimental.CosineDecayRestarts(\n",
" initial_learning_rate,\n",
" first_decay_steps))\n",
"opt = tf.keras.optimizers.SGD(learning_rate=lr_decayed_fn, nesterov=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Generator"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"train_idg = ImageDataGenerator(\n",
" featurewise_center=False, # set input mean to 0 over the dataset\n",
" samplewise_center=False, # set each sample mean to 0\n",
" featurewise_std_normalization=False, # divide inputs by std of the dataset\n",
" samplewise_std_normalization=False, # divide each input by its std\n",
" zca_whitening=False, # apply ZCA whitening\n",
" shear_range=0.05,\n",
" rotation_range=50, # randomly rotate images in the range (degrees, 0 to 180)\n",
" width_shift_range=0.1, # randomly shift images horizontally (fraction of total width)\n",
" height_shift_range=0.1, # randomly shift images vertically (fraction of total height)\n",
" horizontal_flip=True,\n",
" rescale=1./255)\n",
"valid_idg = ImageDataGenerator(rescale=1./255)\n",
"training_data = pd.read_csv(f'train_0.csv') \n",
"training_data['Image'] = training_data['Image'].apply(png)\n",
"\n",
"validation_data = pd.read_csv(f'valid_0.csv')\n",
"validation_data['Image'] = validation_data['Image'].apply(png)\n",
"\n",
"columns=['any','epidural','intraparenchymal','intraventricular', 'subarachnoid','subdural']\n",
"\n",
"#train_data_generator = train_idg.flow_from_dataframe(training_data, directory = image_dir,\n",
"# x_col = \"Image\", y_col = columns,batch_size=64,\n",
"# class_mode=\"raw\", target_size=(224,224), shuffle = True)\n",
"#valid_data_generator = valid_idg.flow_from_dataframe(validation_data, directory = image_dir,\n",
"# x_col = \"Image\", y_col = columns,batch_size=64,\n",
"# class_mode = \"raw\",target_size=(224,224), shuffle = False)"
]
},
{
"cell_type": "code",
"execution_count": 40,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Found 257598 validated image filenames.\n",
"Found 64320 validated image filenames.\n"
]
}
],
"source": [
"train_under_generator = train_idg.flow_from_dataframe(l, directory = image_dir,\n",
" x_col = \"Image\", y_col = columns,batch_size=64,\n",
" class_mode=\"raw\", target_size=(224,224), shuffle = True)\n",
"valid_under_generator = valid_idg.flow_from_dataframe(m, directory = image_dir,\n",
" x_col = \"Image\", y_col = columns,batch_size=64,\n",
" class_mode = \"raw\",target_size=(224,224), shuffle = False)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Undersamping"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"def undersample(dataframe,steps,batch_size):\n",
" part = np.int(steps/3 * batch_size)\n",
" zero_ids = np.random.choice(dataframe.loc[dataframe[\"any\"] == 0].index.values, size=2*part, replace=False)\n",
" hot_ids = np.random.choice(dataframe.loc[dataframe[\"any\"] == 1].index.values, size=1*part, replace=False)\n",
" data_ids = list(set(zero_ids).union(hot_ids))\n",
" np.random.shuffle(data_ids)\n",
" return data_ids\n",
" "
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"257598\n"
]
}
],
"source": [
"train_indices = undersample(training_data, 8050,32)\n",
"print(len(train_indices))"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"64320\n"
]
}
],
"source": [
"valid_indices = undersample(validation_data, 2010,32)\n",
"print(len(valid_indices))"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"l = training_data[training_data.index.isin(train_indices)]\n",
"m = validation_data[validation_data.index.isin(valid_indices)]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Model"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<tensorflow.python.keras.engine.input_layer.InputLayer object at 0x7f3da7d24ba8>\n",
"<tensorflow.python.keras.layers.convolutional.ZeroPadding2D object at 0x7f3da7d3f6d8>\n",
"<tensorflow.python.keras.layers.convolutional.Conv2D object at 0x7f3da76be400>\n",
"<tensorflow.python.keras.layers.normalization_v2.BatchNormalization object at 0x7f3da765a630>\n",
"<tensorflow.python.keras.layers.advanced_activations.ReLU object at 0x7f3da765ad30>\n",
"<tensorflow.python.keras.layers.convolutional.DepthwiseConv2D object at 0x7f3da765ab70>\n",
"<tensorflow.python.keras.layers.normalization_v2.BatchNormalization object at 0x7f3da7ce64e0>\n",
"<tensorflow.python.keras.layers.advanced_activations.ReLU object at 0x7f3da7ce6d30>\n",
"<tensorflow.python.keras.layers.convolutional.Conv2D object at 0x7f3da7ce6668>\n",
"<tensorflow.python.keras.layers.normalization_v2.BatchNormalization object at 0x7f3da766d0f0>\n",
"<tensorflow.python.keras.layers.convolutional.Conv2D object at 0x7f3da766d5f8>\n",
"<tensorflow.python.keras.layers.normalization_v2.BatchNormalization object at 0x7f3da7609128>\n",
"<tensorflow.python.keras.layers.advanced_activations.ReLU object at 0x7f3da7609c88>\n",
"<tensorflow.python.keras.layers.convolutional.ZeroPadding2D object at 0x7f3da7609d68>\n",
"<tensorflow.python.keras.layers.convolutional.DepthwiseConv2D object at 0x7f3da76217f0>\n",
"<tensorflow.python.keras.layers.normalization_v2.BatchNormalization object at 0x7f3da76279e8>\n",
"<tensorflow.python.keras.layers.advanced_activations.ReLU object at 0x7f3da7627c50>\n",
"<tensorflow.python.keras.layers.convolutional.Conv2D object at 0x7f3da762f128>\n",
"<tensorflow.python.keras.layers.normalization_v2.BatchNormalization object at 0x7f3da75ca2b0>\n",
"<tensorflow.python.keras.layers.convolutional.Conv2D object at 0x7f3da75cac18>\n",
"<tensorflow.python.keras.layers.normalization_v2.BatchNormalization object at 0x7f3da75e46a0>\n",
"<tensorflow.python.keras.layers.advanced_activations.ReLU object at 0x7f3da75ea240>\n",
"<tensorflow.python.keras.layers.convolutional.DepthwiseConv2D object at 0x7f3da75ea358>\n",
"<tensorflow.python.keras.layers.normalization_v2.BatchNormalization object at 0x7f3da7587dd8>\n",
"<tensorflow.python.keras.layers.advanced_activations.ReLU object at 0x7f3da7587e10>\n",
"<tensorflow.python.keras.layers.convolutional.Conv2D object at 0x7f3da758b2e8>\n",
"<tensorflow.python.keras.layers.normalization_v2.BatchNormalization object at 0x7f3da75a4780>\n",
"<tensorflow.python.keras.layers.merge.Add object at 0x7f3da75a4d30>\n"
]
}
],
"source": [
"from tensorflow.keras.applications.mobilenet_v2 import MobileNetV2\n",
"\n",
"\n",
"base_model = MobileNetV2(weights='imagenet', include_top=False, input_shape=(224,224,3))\n",
"\n",
"for layer in base_model.layers[:28]:\n",
" layer.trainable = False"
]
},
{
"cell_type": "code",
"execution_count": 34,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Model loaded.\n",
"Model: \"functional_3\"\n",
"__________________________________________________________________________________________________\n",
"Layer (type) Output Shape Param # Connected to \n",
"==================================================================================================\n",
"input_11 (InputLayer) [(None, 224, 224, 3) 0 \n",
"__________________________________________________________________________________________________\n",
"Conv1_pad (ZeroPadding2D) (None, 225, 225, 3) 0 input_11[0][0] \n",
"__________________________________________________________________________________________________\n",
"Conv1 (Conv2D) (None, 112, 112, 32) 864 Conv1_pad[0][0] \n",
"__________________________________________________________________________________________________\n",
"bn_Conv1 (BatchNormalization) (None, 112, 112, 32) 128 Conv1[0][0] \n",
"__________________________________________________________________________________________________\n",
"Conv1_relu (ReLU) (None, 112, 112, 32) 0 bn_Conv1[0][0] \n",
"__________________________________________________________________________________________________\n",
"expanded_conv_depthwise (Depthw (None, 112, 112, 32) 288 Conv1_relu[0][0] \n",
"__________________________________________________________________________________________________\n",
"expanded_conv_depthwise_BN (Bat (None, 112, 112, 32) 128 expanded_conv_depthwise[0][0] \n",
"__________________________________________________________________________________________________\n",
"expanded_conv_depthwise_relu (R (None, 112, 112, 32) 0 expanded_conv_depthwise_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"expanded_conv_project (Conv2D) (None, 112, 112, 16) 512 expanded_conv_depthwise_relu[0][0\n",
"__________________________________________________________________________________________________\n",
"expanded_conv_project_BN (Batch (None, 112, 112, 16) 64 expanded_conv_project[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_1_expand (Conv2D) (None, 112, 112, 96) 1536 expanded_conv_project_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_1_expand_BN (BatchNormali (None, 112, 112, 96) 384 block_1_expand[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_1_expand_relu (ReLU) (None, 112, 112, 96) 0 block_1_expand_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_1_pad (ZeroPadding2D) (None, 113, 113, 96) 0 block_1_expand_relu[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_1_depthwise (DepthwiseCon (None, 56, 56, 96) 864 block_1_pad[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_1_depthwise_BN (BatchNorm (None, 56, 56, 96) 384 block_1_depthwise[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_1_depthwise_relu (ReLU) (None, 56, 56, 96) 0 block_1_depthwise_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_1_project (Conv2D) (None, 56, 56, 24) 2304 block_1_depthwise_relu[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_1_project_BN (BatchNormal (None, 56, 56, 24) 96 block_1_project[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_2_expand (Conv2D) (None, 56, 56, 144) 3456 block_1_project_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_2_expand_BN (BatchNormali (None, 56, 56, 144) 576 block_2_expand[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_2_expand_relu (ReLU) (None, 56, 56, 144) 0 block_2_expand_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_2_depthwise (DepthwiseCon (None, 56, 56, 144) 1296 block_2_expand_relu[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_2_depthwise_BN (BatchNorm (None, 56, 56, 144) 576 block_2_depthwise[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_2_depthwise_relu (ReLU) (None, 56, 56, 144) 0 block_2_depthwise_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_2_project (Conv2D) (None, 56, 56, 24) 3456 block_2_depthwise_relu[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_2_project_BN (BatchNormal (None, 56, 56, 24) 96 block_2_project[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_2_add (Add) (None, 56, 56, 24) 0 block_1_project_BN[0][0] \n",
" block_2_project_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_3_expand (Conv2D) (None, 56, 56, 144) 3456 block_2_add[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_3_expand_BN (BatchNormali (None, 56, 56, 144) 576 block_3_expand[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_3_expand_relu (ReLU) (None, 56, 56, 144) 0 block_3_expand_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_3_pad (ZeroPadding2D) (None, 57, 57, 144) 0 block_3_expand_relu[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_3_depthwise (DepthwiseCon (None, 28, 28, 144) 1296 block_3_pad[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_3_depthwise_BN (BatchNorm (None, 28, 28, 144) 576 block_3_depthwise[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_3_depthwise_relu (ReLU) (None, 28, 28, 144) 0 block_3_depthwise_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_3_project (Conv2D) (None, 28, 28, 32) 4608 block_3_depthwise_relu[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_3_project_BN (BatchNormal (None, 28, 28, 32) 128 block_3_project[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_4_expand (Conv2D) (None, 28, 28, 192) 6144 block_3_project_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_4_expand_BN (BatchNormali (None, 28, 28, 192) 768 block_4_expand[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_4_expand_relu (ReLU) (None, 28, 28, 192) 0 block_4_expand_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_4_depthwise (DepthwiseCon (None, 28, 28, 192) 1728 block_4_expand_relu[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_4_depthwise_BN (BatchNorm (None, 28, 28, 192) 768 block_4_depthwise[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_4_depthwise_relu (ReLU) (None, 28, 28, 192) 0 block_4_depthwise_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_4_project (Conv2D) (None, 28, 28, 32) 6144 block_4_depthwise_relu[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_4_project_BN (BatchNormal (None, 28, 28, 32) 128 block_4_project[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_4_add (Add) (None, 28, 28, 32) 0 block_3_project_BN[0][0] \n",
" block_4_project_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_5_expand (Conv2D) (None, 28, 28, 192) 6144 block_4_add[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_5_expand_BN (BatchNormali (None, 28, 28, 192) 768 block_5_expand[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_5_expand_relu (ReLU) (None, 28, 28, 192) 0 block_5_expand_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_5_depthwise (DepthwiseCon (None, 28, 28, 192) 1728 block_5_expand_relu[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_5_depthwise_BN (BatchNorm (None, 28, 28, 192) 768 block_5_depthwise[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_5_depthwise_relu (ReLU) (None, 28, 28, 192) 0 block_5_depthwise_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_5_project (Conv2D) (None, 28, 28, 32) 6144 block_5_depthwise_relu[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_5_project_BN (BatchNormal (None, 28, 28, 32) 128 block_5_project[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_5_add (Add) (None, 28, 28, 32) 0 block_4_add[0][0] \n",
" block_5_project_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_6_expand (Conv2D) (None, 28, 28, 192) 6144 block_5_add[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_6_expand_BN (BatchNormali (None, 28, 28, 192) 768 block_6_expand[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_6_expand_relu (ReLU) (None, 28, 28, 192) 0 block_6_expand_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_6_pad (ZeroPadding2D) (None, 29, 29, 192) 0 block_6_expand_relu[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_6_depthwise (DepthwiseCon (None, 14, 14, 192) 1728 block_6_pad[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_6_depthwise_BN (BatchNorm (None, 14, 14, 192) 768 block_6_depthwise[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_6_depthwise_relu (ReLU) (None, 14, 14, 192) 0 block_6_depthwise_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_6_project (Conv2D) (None, 14, 14, 64) 12288 block_6_depthwise_relu[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_6_project_BN (BatchNormal (None, 14, 14, 64) 256 block_6_project[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_7_expand (Conv2D) (None, 14, 14, 384) 24576 block_6_project_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_7_expand_BN (BatchNormali (None, 14, 14, 384) 1536 block_7_expand[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_7_expand_relu (ReLU) (None, 14, 14, 384) 0 block_7_expand_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_7_depthwise (DepthwiseCon (None, 14, 14, 384) 3456 block_7_expand_relu[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_7_depthwise_BN (BatchNorm (None, 14, 14, 384) 1536 block_7_depthwise[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_7_depthwise_relu (ReLU) (None, 14, 14, 384) 0 block_7_depthwise_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_7_project (Conv2D) (None, 14, 14, 64) 24576 block_7_depthwise_relu[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_7_project_BN (BatchNormal (None, 14, 14, 64) 256 block_7_project[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_7_add (Add) (None, 14, 14, 64) 0 block_6_project_BN[0][0] \n",
" block_7_project_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_8_expand (Conv2D) (None, 14, 14, 384) 24576 block_7_add[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_8_expand_BN (BatchNormali (None, 14, 14, 384) 1536 block_8_expand[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_8_expand_relu (ReLU) (None, 14, 14, 384) 0 block_8_expand_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_8_depthwise (DepthwiseCon (None, 14, 14, 384) 3456 block_8_expand_relu[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_8_depthwise_BN (BatchNorm (None, 14, 14, 384) 1536 block_8_depthwise[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_8_depthwise_relu (ReLU) (None, 14, 14, 384) 0 block_8_depthwise_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_8_project (Conv2D) (None, 14, 14, 64) 24576 block_8_depthwise_relu[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_8_project_BN (BatchNormal (None, 14, 14, 64) 256 block_8_project[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_8_add (Add) (None, 14, 14, 64) 0 block_7_add[0][0] \n",
" block_8_project_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_9_expand (Conv2D) (None, 14, 14, 384) 24576 block_8_add[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_9_expand_BN (BatchNormali (None, 14, 14, 384) 1536 block_9_expand[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_9_expand_relu (ReLU) (None, 14, 14, 384) 0 block_9_expand_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_9_depthwise (DepthwiseCon (None, 14, 14, 384) 3456 block_9_expand_relu[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_9_depthwise_BN (BatchNorm (None, 14, 14, 384) 1536 block_9_depthwise[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_9_depthwise_relu (ReLU) (None, 14, 14, 384) 0 block_9_depthwise_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_9_project (Conv2D) (None, 14, 14, 64) 24576 block_9_depthwise_relu[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_9_project_BN (BatchNormal (None, 14, 14, 64) 256 block_9_project[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_9_add (Add) (None, 14, 14, 64) 0 block_8_add[0][0] \n",
" block_9_project_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_10_expand (Conv2D) (None, 14, 14, 384) 24576 block_9_add[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_10_expand_BN (BatchNormal (None, 14, 14, 384) 1536 block_10_expand[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_10_expand_relu (ReLU) (None, 14, 14, 384) 0 block_10_expand_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_10_depthwise (DepthwiseCo (None, 14, 14, 384) 3456 block_10_expand_relu[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_10_depthwise_BN (BatchNor (None, 14, 14, 384) 1536 block_10_depthwise[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_10_depthwise_relu (ReLU) (None, 14, 14, 384) 0 block_10_depthwise_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_10_project (Conv2D) (None, 14, 14, 96) 36864 block_10_depthwise_relu[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_10_project_BN (BatchNorma (None, 14, 14, 96) 384 block_10_project[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_11_expand (Conv2D) (None, 14, 14, 576) 55296 block_10_project_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_11_expand_BN (BatchNormal (None, 14, 14, 576) 2304 block_11_expand[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_11_expand_relu (ReLU) (None, 14, 14, 576) 0 block_11_expand_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_11_depthwise (DepthwiseCo (None, 14, 14, 576) 5184 block_11_expand_relu[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_11_depthwise_BN (BatchNor (None, 14, 14, 576) 2304 block_11_depthwise[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_11_depthwise_relu (ReLU) (None, 14, 14, 576) 0 block_11_depthwise_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_11_project (Conv2D) (None, 14, 14, 96) 55296 block_11_depthwise_relu[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_11_project_BN (BatchNorma (None, 14, 14, 96) 384 block_11_project[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_11_add (Add) (None, 14, 14, 96) 0 block_10_project_BN[0][0] \n",
" block_11_project_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_12_expand (Conv2D) (None, 14, 14, 576) 55296 block_11_add[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_12_expand_BN (BatchNormal (None, 14, 14, 576) 2304 block_12_expand[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_12_expand_relu (ReLU) (None, 14, 14, 576) 0 block_12_expand_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_12_depthwise (DepthwiseCo (None, 14, 14, 576) 5184 block_12_expand_relu[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_12_depthwise_BN (BatchNor (None, 14, 14, 576) 2304 block_12_depthwise[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_12_depthwise_relu (ReLU) (None, 14, 14, 576) 0 block_12_depthwise_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_12_project (Conv2D) (None, 14, 14, 96) 55296 block_12_depthwise_relu[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_12_project_BN (BatchNorma (None, 14, 14, 96) 384 block_12_project[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_12_add (Add) (None, 14, 14, 96) 0 block_11_add[0][0] \n",
" block_12_project_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_13_expand (Conv2D) (None, 14, 14, 576) 55296 block_12_add[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_13_expand_BN (BatchNormal (None, 14, 14, 576) 2304 block_13_expand[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_13_expand_relu (ReLU) (None, 14, 14, 576) 0 block_13_expand_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_13_pad (ZeroPadding2D) (None, 15, 15, 576) 0 block_13_expand_relu[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_13_depthwise (DepthwiseCo (None, 7, 7, 576) 5184 block_13_pad[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_13_depthwise_BN (BatchNor (None, 7, 7, 576) 2304 block_13_depthwise[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_13_depthwise_relu (ReLU) (None, 7, 7, 576) 0 block_13_depthwise_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_13_project (Conv2D) (None, 7, 7, 160) 92160 block_13_depthwise_relu[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_13_project_BN (BatchNorma (None, 7, 7, 160) 640 block_13_project[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_14_expand (Conv2D) (None, 7, 7, 960) 153600 block_13_project_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_14_expand_BN (BatchNormal (None, 7, 7, 960) 3840 block_14_expand[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_14_expand_relu (ReLU) (None, 7, 7, 960) 0 block_14_expand_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_14_depthwise (DepthwiseCo (None, 7, 7, 960) 8640 block_14_expand_relu[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_14_depthwise_BN (BatchNor (None, 7, 7, 960) 3840 block_14_depthwise[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_14_depthwise_relu (ReLU) (None, 7, 7, 960) 0 block_14_depthwise_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_14_project (Conv2D) (None, 7, 7, 160) 153600 block_14_depthwise_relu[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_14_project_BN (BatchNorma (None, 7, 7, 160) 640 block_14_project[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_14_add (Add) (None, 7, 7, 160) 0 block_13_project_BN[0][0] \n",
" block_14_project_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_15_expand (Conv2D) (None, 7, 7, 960) 153600 block_14_add[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_15_expand_BN (BatchNormal (None, 7, 7, 960) 3840 block_15_expand[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_15_expand_relu (ReLU) (None, 7, 7, 960) 0 block_15_expand_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_15_depthwise (DepthwiseCo (None, 7, 7, 960) 8640 block_15_expand_relu[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_15_depthwise_BN (BatchNor (None, 7, 7, 960) 3840 block_15_depthwise[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_15_depthwise_relu (ReLU) (None, 7, 7, 960) 0 block_15_depthwise_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_15_project (Conv2D) (None, 7, 7, 160) 153600 block_15_depthwise_relu[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_15_project_BN (BatchNorma (None, 7, 7, 160) 640 block_15_project[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_15_add (Add) (None, 7, 7, 160) 0 block_14_add[0][0] \n",
" block_15_project_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_16_expand (Conv2D) (None, 7, 7, 960) 153600 block_15_add[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_16_expand_BN (BatchNormal (None, 7, 7, 960) 3840 block_16_expand[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_16_expand_relu (ReLU) (None, 7, 7, 960) 0 block_16_expand_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_16_depthwise (DepthwiseCo (None, 7, 7, 960) 8640 block_16_expand_relu[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_16_depthwise_BN (BatchNor (None, 7, 7, 960) 3840 block_16_depthwise[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_16_depthwise_relu (ReLU) (None, 7, 7, 960) 0 block_16_depthwise_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_16_project (Conv2D) (None, 7, 7, 320) 307200 block_16_depthwise_relu[0][0] \n",
"__________________________________________________________________________________________________\n",
"block_16_project_BN (BatchNorma (None, 7, 7, 320) 1280 block_16_project[0][0] \n",
"__________________________________________________________________________________________________\n",
"Conv_1 (Conv2D) (None, 7, 7, 1280) 409600 block_16_project_BN[0][0] \n",
"__________________________________________________________________________________________________\n",
"Conv_1_bn (BatchNormalization) (None, 7, 7, 1280) 5120 Conv_1[0][0] \n",
"__________________________________________________________________________________________________\n",
"out_relu (ReLU) (None, 7, 7, 1280) 0 Conv_1_bn[0][0] \n",
"__________________________________________________________________________________________________\n",
"global_average_pooling2d_1 (Glo (None, 1280) 0 out_relu[0][0] \n",
"__________________________________________________________________________________________________\n",
"dense_2 (Dense) (None, 256) 327936 global_average_pooling2d_1[0][0] \n",
"__________________________________________________________________________________________________\n",
"dense_3 (Dense) (None, 6) 1542 dense_2[0][0] \n",
"==================================================================================================\n",
"Total params: 2,587,462\n",
"Trainable params: 2,537,558\n",
"Non-trainable params: 49,904\n",
"__________________________________________________________________________________________________\n"
]
}
],
"source": [
"from tensorflow.keras.applications.mobilenet_v2 import MobileNetV2\n",
"import tensorflow as tf\n",
"from tensorflow.keras.models import Model,Sequential\n",
"from tensorflow.keras.layers import Dense, GlobalAveragePooling2D, Dropout\n",
"\n",
"METRICS = [\n",
" tf.keras.metrics.TruePositives(name='tp'),\n",
" tf.keras.metrics.FalsePositives(name='fp'),\n",
" tf.keras.metrics.TrueNegatives(name='tn'),\n",
" tf.keras.metrics.FalseNegatives(name='fn'), \n",
" tf.keras.metrics.BinaryAccuracy(name='accuracy'),\n",
" tf.keras.metrics.Precision(name='precision'),\n",
" tf.keras.metrics.Recall(name='recall'),\n",
" tf.keras.metrics.AUC(name='auc')\n",
" \n",
"]\n",
"\n",
"\n",
"# create the base pre-trained model\n",
"base_model = MobileNetV2(weights='imagenet', include_top=False, input_shape=(224,224,3))\n",
"print('Model loaded.')\n",
"\n",
"\n",
"\n",
"# add a global spatial average pooling layer\n",
"x = base_model.output\n",
"\n",
"x = GlobalAveragePooling2D()(x)\n",
"net = Dense(256, activation='elu')(x)\n",
"net = Dense(6, activation='sigmoid')(net)\n",
"\n",
"\n",
"# this is the model we will train\n",
"model = Model(inputs=base_model.input, outputs=net)\n",
"\n",
"\n",
"\n",
"# first: train only the top layers (which were randomly initialized)\n",
"# i.e. freeze all convolutional InceptionV3 layers\n",
"#for layer in base_model.layers:\n",
"# layer.trainable = False\n",
"for layer in base_model.layers[:28]:\n",
" layer.trainable = False\n",
"\n",
"\n",
"# compile the model (should be done *after* setting layers to non-trainable)\n",
"model.compile(opt, loss='binary_crossentropy', metrics=METRICS)\n",
"\n",
"\n",
"\n",
"\n",
"model.summary()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Callback"
]
},
{
"cell_type": "code",
"execution_count": 35,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"WARNING:tensorflow:`period` argument is deprecated. Please use `save_freq` to specify the frequency in number of batches seen.\n"
]
}
],
"source": [
"from keras import backend as K\n",
"\n",
"from tensorflow.keras.callbacks import ModelCheckpoint\n",
"\n",
"\n",
"checkpoint = tf.keras.callbacks.ModelCheckpoint('/kaggle/models/mobilenetv2_{epoch:08d}.h5', period=1,mode= 'auto',save_best_only=True) \n",
"\n",
"learning_rate_reduction = tf.keras.callbacks.ReduceLROnPlateau(monitor='val_acc', \n",
" patience=2, \n",
" verbose=1, \n",
" factor=0.5, \n",
" min_lr=0.00001)\n",
"\n",
"callback_list = [checkpoint]\n"
]
},
{
"cell_type": "code",
"execution_count": 36,
"metadata": {},
"outputs": [],
"source": [
"tf.config.experimental_run_functions_eagerly(True)"
]
},
{
"cell_type": "code",
"execution_count": 37,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{0: 1.0, 1: 2.0}"
]
},
"execution_count": 37,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"class_weight = {0:1.0,1:2.0}\n",
"class_weight"
]
},
{
"cell_type": "code",
"execution_count": 41,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Epoch 1/20\n",
"1173/1173 [==============================] - 1328s 1s/step - loss: 0.2700 - tp: 19402.0000 - fp: 8747.0000 - tn: 382086.0000 - fn: 40185.0000 - accuracy: 0.8914 - precision: 0.6893 - recall: 0.3256 - auc: 0.8689 - val_loss: 0.2460 - val_tp: 5447.0000 - val_fp: 1729.0000 - val_tn: 96812.0000 - val_fn: 9676.0000 - val_accuracy: 0.8997 - val_precision: 0.7591 - val_recall: 0.3602 - val_auc: 0.8964\n",
"Epoch 2/20\n",
"1173/1173 [==============================] - 1296s 1s/step - loss: 0.2220 - tp: 29348.0000 - fp: 9754.0000 - tn: 380669.0000 - fn: 30661.0000 - accuracy: 0.9103 - precision: 0.7505 - recall: 0.4891 - auc: 0.9167 - val_loss: 0.2277 - val_tp: 5878.0000 - val_fp: 1266.0000 - val_tn: 97275.0000 - val_fn: 9245.0000 - val_accuracy: 0.9075 - val_precision: 0.8228 - val_recall: 0.3887 - val_auc: 0.9169\n",
"Epoch 3/20\n",
"1173/1173 [==============================] - 1292s 1s/step - loss: 0.2078 - tp: 31038.0000 - fp: 9584.0000 - tn: 381852.0000 - fn: 27958.0000 - accuracy: 0.9167 - precision: 0.7641 - recall: 0.5261 - auc: 0.9265 - val_loss: 0.2301 - val_tp: 5974.0000 - val_fp: 1040.0000 - val_tn: 97501.0000 - val_fn: 9149.0000 - val_accuracy: 0.9104 - val_precision: 0.8517 - val_recall: 0.3950 - val_auc: 0.9232\n",
"Epoch 4/20\n",
"1173/1173 [==============================] - 1279s 1s/step - loss: 0.1949 - tp: 33376.0000 - fp: 9367.0000 - tn: 382104.0000 - fn: 25585.0000 - accuracy: 0.9224 - precision: 0.7809 - recall: 0.5661 - auc: 0.9357 - val_loss: 0.2313 - val_tp: 6112.0000 - val_fp: 986.0000 - val_tn: 97555.0000 - val_fn: 9011.0000 - val_accuracy: 0.9120 - val_precision: 0.8611 - val_recall: 0.4042 - val_auc: 0.9257\n",
"Epoch 5/20\n",
"1173/1173 [==============================] - 1279s 1s/step - loss: 0.1900 - tp: 35090.0000 - fp: 9370.0000 - tn: 381208.0000 - fn: 24764.0000 - accuracy: 0.9242 - precision: 0.7892 - recall: 0.5863 - auc: 0.9401 - val_loss: 0.2177 - val_tp: 6592.0000 - val_fp: 1084.0000 - val_tn: 97457.0000 - val_fn: 8531.0000 - val_accuracy: 0.9154 - val_precision: 0.8588 - val_recall: 0.4359 - val_auc: 0.9314\n",
"Epoch 6/20\n",
"1173/1173 [==============================] - 1283s 1s/step - loss: 0.1875 - tp: 35074.0000 - fp: 9146.0000 - tn: 381913.0000 - fn: 24299.0000 - accuracy: 0.9257 - precision: 0.7932 - recall: 0.5907 - auc: 0.9409 - val_loss: 0.2338 - val_tp: 6123.0000 - val_fp: 868.0000 - val_tn: 97673.0000 - val_fn: 9000.0000 - val_accuracy: 0.9132 - val_precision: 0.8758 - val_recall: 0.4049 - val_auc: 0.9268\n",
"Epoch 7/20\n",
"1173/1173 [==============================] - 1264s 1s/step - loss: 0.1821 - tp: 35762.0000 - fp: 9263.0000 - tn: 381927.0000 - fn: 23468.0000 - accuracy: 0.9273 - precision: 0.7943 - recall: 0.6038 - auc: 0.9449 - val_loss: 0.2083 - val_tp: 7028.0000 - val_fp: 1008.0000 - val_tn: 97533.0000 - val_fn: 8095.0000 - val_accuracy: 0.9199 - val_precision: 0.8746 - val_recall: 0.4647 - val_auc: 0.9377\n",
"Epoch 8/20\n",
"1173/1173 [==============================] - 1273s 1s/step - loss: 0.1754 - tp: 37179.0000 - fp: 8857.0000 - tn: 382099.0000 - fn: 22297.0000 - accuracy: 0.9308 - precision: 0.8076 - recall: 0.6251 - auc: 0.9489 - val_loss: 0.2053 - val_tp: 7383.0000 - val_fp: 1125.0000 - val_tn: 97416.0000 - val_fn: 7740.0000 - val_accuracy: 0.9220 - val_precision: 0.8678 - val_recall: 0.4882 - val_auc: 0.9381\n",
"Epoch 9/20\n",
"1173/1173 [==============================] - 1268s 1s/step - loss: 0.1715 - tp: 38204.0000 - fp: 8739.0000 - tn: 381841.0000 - fn: 21636.0000 - accuracy: 0.9326 - precision: 0.8138 - recall: 0.6384 - auc: 0.9514 - val_loss: 0.2032 - val_tp: 7415.0000 - val_fp: 1048.0000 - val_tn: 97493.0000 - val_fn: 7708.0000 - val_accuracy: 0.9230 - val_precision: 0.8762 - val_recall: 0.4903 - val_auc: 0.9394\n",
"Epoch 10/20\n",
"1173/1173 [==============================] - 1268s 1s/step - loss: 0.1665 - tp: 38293.0000 - fp: 8435.0000 - tn: 382620.0000 - fn: 21084.0000 - accuracy: 0.9345 - precision: 0.8195 - recall: 0.6449 - auc: 0.9539 - val_loss: 0.1997 - val_tp: 7537.0000 - val_fp: 1000.0000 - val_tn: 97541.0000 - val_fn: 7586.0000 - val_accuracy: 0.9245 - val_precision: 0.8829 - val_recall: 0.4984 - val_auc: 0.9421\n",
"Epoch 11/20\n",
"1173/1173 [==============================] - 1270s 1s/step - loss: 0.1663 - tp: 38231.0000 - fp: 8411.0000 - tn: 382751.0000 - fn: 21039.0000 - accuracy: 0.9346 - precision: 0.8197 - recall: 0.6450 - auc: 0.9539 - val_loss: 0.1940 - val_tp: 7785.0000 - val_fp: 1068.0000 - val_tn: 97473.0000 - val_fn: 7338.0000 - val_accuracy: 0.9260 - val_precision: 0.8794 - val_recall: 0.5148 - val_auc: 0.9440\n",
"Epoch 12/20\n",
"1173/1173 [==============================] - 1269s 1s/step - loss: 0.1655 - tp: 38954.0000 - fp: 8580.0000 - tn: 382129.0000 - fn: 20769.0000 - accuracy: 0.9348 - precision: 0.8195 - recall: 0.6522 - auc: 0.9547 - val_loss: 0.1959 - val_tp: 7668.0000 - val_fp: 1026.0000 - val_tn: 97515.0000 - val_fn: 7455.0000 - val_accuracy: 0.9254 - val_precision: 0.8820 - val_recall: 0.5070 - val_auc: 0.9438\n",
"Epoch 13/20\n",
"1173/1173 [==============================] - 1274s 1s/step - loss: 0.1655 - tp: 39098.0000 - fp: 8387.0000 - tn: 382257.0000 - fn: 20678.0000 - accuracy: 0.9355 - precision: 0.8234 - recall: 0.6541 - auc: 0.9548 - val_loss: 0.1883 - val_tp: 7970.0000 - val_fp: 1105.0000 - val_tn: 97436.0000 - val_fn: 7153.0000 - val_accuracy: 0.9273 - val_precision: 0.8782 - val_recall: 0.5270 - val_auc: 0.9461\n",
"Epoch 14/20\n",
"1173/1173 [==============================] - 1263s 1s/step - loss: 0.1620 - tp: 38931.0000 - fp: 8356.0000 - tn: 382832.0000 - fn: 20313.0000 - accuracy: 0.9364 - precision: 0.8233 - recall: 0.6571 - auc: 0.9565 - val_loss: 0.1945 - val_tp: 7884.0000 - val_fp: 952.0000 - val_tn: 97589.0000 - val_fn: 7239.0000 - val_accuracy: 0.9279 - val_precision: 0.8923 - val_recall: 0.5213 - val_auc: 0.9457\n",
"Epoch 15/20\n",
"1173/1173 [==============================] - 1269s 1s/step - loss: 0.1598 - tp: 39738.0000 - fp: 8143.0000 - tn: 382553.0000 - fn: 19998.0000 - accuracy: 0.9375 - precision: 0.8299 - recall: 0.6652 - auc: 0.9577 - val_loss: 0.2045 - val_tp: 7595.0000 - val_fp: 810.0000 - val_tn: 97731.0000 - val_fn: 7528.0000 - val_accuracy: 0.9266 - val_precision: 0.9036 - val_recall: 0.5022 - val_auc: 0.9426\n",
"Epoch 16/20\n",
"1173/1173 [==============================] - 1265s 1s/step - loss: 0.1563 - tp: 40287.0000 - fp: 8134.0000 - tn: 382563.0000 - fn: 19448.0000 - accuracy: 0.9388 - precision: 0.8320 - recall: 0.6744 - auc: 0.9597 - val_loss: 0.1836 - val_tp: 8284.0000 - val_fp: 981.0000 - val_tn: 97560.0000 - val_fn: 6839.0000 - val_accuracy: 0.9312 - val_precision: 0.8941 - val_recall: 0.5478 - val_auc: 0.9502\n",
"Epoch 17/20\n",
"1173/1173 [==============================] - 1271s 1s/step - loss: 0.1519 - tp: 40075.0000 - fp: 7678.0000 - tn: 383929.0000 - fn: 18750.0000 - accuracy: 0.9413 - precision: 0.8392 - recall: 0.6813 - auc: 0.9610 - val_loss: 0.1840 - val_tp: 8377.0000 - val_fp: 1005.0000 - val_tn: 97536.0000 - val_fn: 6746.0000 - val_accuracy: 0.9318 - val_precision: 0.8929 - val_recall: 0.5539 - val_auc: 0.9494\n",
"Epoch 18/20\n",
"1173/1173 [==============================] - 1261s 1s/step - loss: 0.1519 - tp: 40709.0000 - fp: 7828.0000 - tn: 383056.0000 - fn: 18839.0000 - accuracy: 0.9408 - precision: 0.8387 - recall: 0.6836 - auc: 0.9616 - val_loss: 0.1849 - val_tp: 8335.0000 - val_fp: 947.0000 - val_tn: 97594.0000 - val_fn: 6788.0000 - val_accuracy: 0.9319 - val_precision: 0.8980 - val_recall: 0.5511 - val_auc: 0.9505\n",
"Epoch 19/20\n",
"1173/1173 [==============================] - 1265s 1s/step - loss: 0.1503 - tp: 41186.0000 - fp: 7856.0000 - tn: 382971.0000 - fn: 18419.0000 - accuracy: 0.9417 - precision: 0.8398 - recall: 0.6910 - auc: 0.9627 - val_loss: 0.1790 - val_tp: 8654.0000 - val_fp: 1112.0000 - val_tn: 97429.0000 - val_fn: 6469.0000 - val_accuracy: 0.9333 - val_precision: 0.8861 - val_recall: 0.5722 - val_auc: 0.9517\n",
"Epoch 20/20\n",
"1173/1173 [==============================] - 1260s 1s/step - loss: 0.1476 - tp: 41101.0000 - fp: 7569.0000 - tn: 383508.0000 - fn: 18254.0000 - accuracy: 0.9427 - precision: 0.8445 - recall: 0.6925 - auc: 0.9636 - val_loss: 0.1780 - val_tp: 8662.0000 - val_fp: 1083.0000 - val_tn: 97458.0000 - val_fn: 6461.0000 - val_accuracy: 0.9336 - val_precision: 0.8889 - val_recall: 0.5728 - val_auc: 0.9520\n"
]
}
],
"source": [
"\n",
"\n",
"\n",
"num_epochs = 20\n",
"\n",
"batch_size = 512\n",
"training_steps = len(training_data) // batch_size\n",
"validation_step = len(validation_data) // batch_size\n",
"\n",
"\n",
"\n",
"\n",
"\n",
"# FIT THE MODEL\n",
"history = model.fit(train_under_generator,\n",
" epochs=num_epochs,\n",
" steps_per_epoch=training_steps,\n",
" callbacks=callback_list,\n",
" class_weight=class_weight,\n",
" validation_data=valid_under_generator,\n",
" validation_steps= validation_step\n",
" ) \n",
"\n",
"\n",
"\n",
"\n",
"\n",
"tf.keras.backend.clear_session()\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Evalution"
]
},
{
"cell_type": "code",
"execution_count": 42,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"WARNING:tensorflow:From <ipython-input-42-b13240840368>:1: Model.evaluate_generator (from tensorflow.python.keras.engine.training) is deprecated and will be removed in a future version.\n",
"Instructions for updating:\n",
"Please use Model.evaluate, which supports generators.\n",
"[0.1724531054496765, 29916.0, 3813.0, 331362.0, 20829.0, 0.9361472129821777, 0.8869518637657166, 0.5895358920097351, 0.9536344408988953]\n"
]
}
],
"source": [
"valid_predict = model.evaluate_generator(valid_under_generator)\n",
"print(valid_predict)"
]
},
{
"cell_type": "code",
"execution_count": 43,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['loss', 'tp', 'fp', 'tn', 'fn', 'accuracy', 'precision', 'recall', 'auc']"
]
},
"execution_count": 43,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"model.metrics_names"
]
},
{
"cell_type": "code",
"execution_count": 44,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"---------------\n",
"\n",
"validation data **loss** value = 0.1724531054496765\n",
"\n",
"---------------\n",
"\n",
"validation data **true positive** value = 29916.0\n",
"\n",
"---------------\n",
"\n",
"validation data **false positive** value = 3813.0\n",
"\n",
"---------------\n",
"\n",
"validation data **true negative** value = 331362.0\n",
"\n",
"---------------\n",
"\n",
"validation data **false negative** value = 20829.0\n",
"\n",
"---------------\n",
"\n",
"validation data **accuracy** value = 0.9361472129821777\n",
"\n",
"---------------\n",
"\n",
"validation data **precision** value = 0.8869518637657166\n",
"\n",
"---------------\n",
"\n",
"validation data **recall* value = 0.5895358920097351\n",
"\n",
"---------------\n",
"\n",
"validation data **AUC* value = 0.9536344408988953\n",
"\n",
"---------------\n",
"\n"
]
}
],
"source": [
"print('\\n---------------\\n')\n",
"print('validation data **loss** value =', valid_predict[0])\n",
"print('\\n---------------\\n')\n",
"print('validation data **true positive** value = ', valid_predict[1])\n",
"print('\\n---------------\\n')\n",
"print('validation data **false positive** value =', valid_predict[2])\n",
"print('\\n---------------\\n')\n",
"print('validation data **true negative** value =', valid_predict[3])\n",
"print('\\n---------------\\n')\n",
"print('validation data **false negative** value =', valid_predict[4])\n",
"print('\\n---------------\\n')\n",
"print('validation data **accuracy** value = ', valid_predict[5])\n",
"print('\\n---------------\\n')\n",
"print('validation data **precision** value =', valid_predict[6])\n",
"print('\\n---------------\\n')\n",
"print('validation data **recall* value =', valid_predict[7])\n",
"print('\\n---------------\\n')\n",
"print('validation data **AUC* value =', valid_predict[8])\n",
"print('\\n---------------\\n')"
]
},
{
"cell_type": "code",
"execution_count": 65,
"metadata": {},
"outputs": [],
"source": [
"y_true = m[['any','epidural','intraparenchymal','intraventricular', 'subarachnoid','subdural']].reset_index(drop=True)\n",
"\n",
"Y_pred = model.predict_generator(valid_under_generator)\n",
"preds = np.where(Y_pred < 0.25, 0, 1)\n",
"\n",
"\n",
"\n",
"#val = 0.25\n",
"\n",
"#Y_pred[Y_pred>=val]=1\n",
"#Y_pred[Y_pred<val]=0"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Classifcation Report"
]
},
{
"cell_type": "code",
"execution_count": 66,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Classification Report\n",
" precision recall f1-score support\n",
"\n",
" any 0.88 0.81 0.84 21440\n",
" epidural 0.09 0.02 0.04 571\n",
"intraparenchymal 0.73 0.79 0.76 6890\n",
"intraventricular 0.72 0.80 0.76 5123\n",
" subarachnoid 0.65 0.56 0.61 7218\n",
" subdural 0.73 0.56 0.63 9503\n",
"\n",
" micro avg 0.78 0.72 0.75 50745\n",
" macro avg 0.63 0.59 0.61 50745\n",
" weighted avg 0.77 0.72 0.74 50745\n",
" samples avg 0.24 0.24 0.23 50745\n",
"\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/ubuntu/anaconda3/envs/tensorflow2_p36/lib/python3.6/site-packages/sklearn/metrics/_classification.py:1272: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in samples with no predicted labels. Use `zero_division` parameter to control this behavior.\n",
" _warn_prf(average, modifier, msg_start, len(result))\n",
"/home/ubuntu/anaconda3/envs/tensorflow2_p36/lib/python3.6/site-packages/sklearn/metrics/_classification.py:1272: UndefinedMetricWarning: Recall and F-score are ill-defined and being set to 0.0 in samples with no true labels. Use `zero_division` parameter to control this behavior.\n",
" _warn_prf(average, modifier, msg_start, len(result))\n"
]
}
],
"source": [
"print('Classification Report')\n",
"target_names = ['any','epidural','intraparenchymal','intraventricular', 'subarachnoid','subdural']\n",
"print(classification_report(y_true, preds, target_names=target_names))"
]
},
{
"cell_type": "code",
"execution_count": 63,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 1008x576 with 6 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"import seaborn as sns\n",
"from sklearn.metrics import multilabel_confusion_matrix\n",
"# Creating multilabel confusion matrix\n",
"confusion = multilabel_confusion_matrix(y_true, preds)\n",
"mlb= ['any','epidural','intraparenchymal','intraventricular', 'subarachnoid','subdural']\n",
"# Plot confusion matrix \n",
"fig = plt.figure(figsize = (14, 8))\n",
"for i, (label, matrix) in enumerate(zip(mlb, confusion)):\n",
" plt.subplot(f'23{i+1}')\n",
" labels = [f'not_{label}', label]\n",
" sns.heatmap(matrix, annot = True, square = True, fmt = 'd', cbar = False, cmap = 'Blues', \n",
" xticklabels = labels, yticklabels = labels, linecolor = 'black', linewidth = 1)\n",
" plt.title(labels[0])\n",
"\n",
"plt.tight_layout()\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# AUC_ROC_SCORE"
]
},
{
"cell_type": "code",
"execution_count": 64,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"0.7906662051891526\n"
]
}
],
"source": [
"auc = roc_auc_score(y_true, preds)\n",
"print(auc)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# ACCURACY AND LOSS PLOT"
]
},
{
"cell_type": "code",
"execution_count": 50,
"metadata": {},
"outputs": [],
"source": [
"def plot_training(H):\n",
" # construct a plot that plots and saves the training history\n",
" with plt.xkcd():\n",
" plt.figure(figsize = (10,10))\n",
" plt.plot(H.epoch,H.history[\"accuracy\"], label=\"train_acc\")\n",
" plt.plot(H.epoch,H.history[\"val_accuracy\"], label=\"val_acc\")\n",
" plt.title(\"Training Accuracy\")\n",
" plt.xlabel(\"Epoch #\")\n",
" plt.ylabel(\"Accuracy\")\n",
" plt.legend(loc=\"lower left\")\n",
" plt.show()"
]
},
{
"cell_type": "code",
"execution_count": 51,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"findfont: Font family ['xkcd', 'xkcd Script', 'Humor Sans', 'Comic Sans MS'] not found. Falling back to DejaVu Sans.\n",
"findfont: Font family ['xkcd', 'xkcd Script', 'Humor Sans', 'Comic Sans MS'] not found. Falling back to DejaVu Sans.\n"
]
},
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 720x720 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"plot_training(history)"
]
},
{
"cell_type": "code",
"execution_count": 52,
"metadata": {},
"outputs": [],
"source": [
"def plot_training(H):\n",
" # construct a plot that plots and saves the training history\n",
" with plt.xkcd():\n",
" plt.figure(figsize = (10,10))\n",
" plt.plot(H.epoch,H.history[\"loss\"], label=\"train_loss\")\n",
" plt.plot(H.epoch,H.history[\"val_loss\"], label=\"val_loss\")\n",
" plt.title(\"Training Loss\")\n",
" plt.xlabel(\"Epoch #\")\n",
" plt.ylabel(\"Loss\")\n",
" plt.legend(loc=\"lower left\")\n",
" plt.show()"
]
},
{
"cell_type": "code",
"execution_count": 53,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 720x720 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"plot_training(history)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"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": "3.6.10"
}
},
"nbformat": 4,
"nbformat_minor": 4
}