{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.7.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# RSNA 2022 Cerical Spine Fracture Detection\n**CSCI217 Project**","metadata":{}},{"cell_type":"markdown","source":"## Import Libraries","metadata":{}},{"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\n\nimport tensorflow as tf\nimport tensorflow.keras.layers as tfl\nfrom tensorflow.keras import backend as K\nfrom sklearn.model_selection import StratifiedKFold\nfrom tensorflow.keras.preprocessing.image import load_img, img_to_array\nfrom tensorflow.keras.applications import EfficientNetB0\n\nimport os\nimport cv2\nimport glob\nimport pydicom as dicom\nimport nibabel as nib\nimport sys","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"## Load Data","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#### Load dataframes","metadata":{}},{"cell_type":"code","source":"df_train = pd.read_csv(\"/kaggle/input/rsna-2022-cervical-spine-fracture-detection/train.csv\")\ndf_test = pd.DataFrame({\"row_id\": ['1.2.826.0.1.3680043.22327_C1', '1.2.826.0.1.3680043.25399_C1', '1.2.826.0.1.3680043.5876_C1'], \n \"StudyInstanceUID\": ['1.2.826.0.1.3680043.22327', '1.2.826.0.1.3680043.25399', '1.2.826.0.1.3680043.5876'], \n \"prediction_type\": [\"C1\", \"C1\", \"C1\"]}) \n\ntrain_images_dir = '/kaggle/input/rsna-2022-cervical-spine-fracture-detection/train_images'\ntest_images_dir = '/kaggle/input/rsna-2022-cervical-spine-fracture-detection/test_images'\n\nnew_submission = []\nmeans = dict(zip(df_train.columns[1:], np.average(df_train.iloc[:,1:], axis=0, weights=df_train[\"patient_overall\"] + 1)))\nprediction_type = df_test['prediction_type'].tolist()\nsubmission = pd.read_csv('/kaggle/input/rsna-2022-cervical-spine-fracture-detection/sample_submission.csv')\nfor i in range(len(submission)): \n new_submission.append(means[prediction_type[i]])\nsubmission['fractured'] = new_submission\n\nprediction_type_mapping = df_test['prediction_type'].map({'C1': 0, 'C2': 1, 'C3': 2, 'C4': 3, 'C5': 4, 'C6': 5, 'C7': 6}).values\n\ndf_train.head()","metadata":{"execution":{"iopub.status.busy":"2023-01-07T08:52:07.704614Z","iopub.execute_input":"2023-01-07T08:52:07.705236Z","iopub.status.idle":"2023-01-07T08:52:07.757577Z","shell.execute_reply.started":"2023-01-07T08:52:07.705202Z","shell.execute_reply":"2023-01-07T08:52:07.756685Z"},"trusted":true},"execution_count":2,"outputs":[{"execution_count":2,"output_type":"execute_result","data":{"text/plain":" StudyInstanceUID patient_overall C1 C2 C3 C4 C5 C6 C7\n0 1.2.826.0.1.3680043.6200 1 1 1 0 0 0 0 0\n1 1.2.826.0.1.3680043.27262 1 0 1 0 0 0 0 0\n2 1.2.826.0.1.3680043.21561 1 0 1 0 0 0 0 0\n3 1.2.826.0.1.3680043.12351 0 0 0 0 0 0 0 0\n4 1.2.826.0.1.3680043.1363 1 0 0 0 0 1 0 0","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
StudyInstanceUIDpatient_overallC1C2C3C4C5C6C7
01.2.826.0.1.3680043.620011100000
11.2.826.0.1.3680043.2726210100000
21.2.826.0.1.3680043.2156110100000
31.2.826.0.1.3680043.1235100000000
41.2.826.0.1.3680043.136310000100
\n
"},"metadata":{}}]},{"cell_type":"markdown","source":"#### Load Dicom Helper Function","metadata":{}},{"cell_type":"code","source":"def load_dicom(path, size = 64):\n img=dicom.dcmread(path)\n img.PhotometricInterpretation = 'YBR_FULL'\n data=img.pixel_array\n data=data-np.min(data)\n if np.max(data) != 0:\n data=data/np.max(data)\n data=(data*255).astype(np.uint8) \n return cv2.cvtColor(data.reshape(512, 512), cv2.COLOR_GRAY2RGB)\n\n \npatients = sorted(os.listdir(train_images_dir))","metadata":{"execution":{"iopub.status.busy":"2023-01-07T08:52:10.46423Z","iopub.execute_input":"2023-01-07T08:52:10.464606Z","iopub.status.idle":"2023-01-07T08:52:10.687257Z","shell.execute_reply.started":"2023-01-07T08:52:10.464573Z","shell.execute_reply":"2023-01-07T08:52:10.686252Z"},"trusted":true},"execution_count":3,"outputs":[]},{"cell_type":"markdown","source":"#### visualize Images","metadata":{}},{"cell_type":"code","source":"image_file = glob.glob(\"/kaggle/input/rsna-2022-cervical-spine-fracture-detection/train_images/1.2.826.0.1.3680043.10001/*.dcm\")\nplt.figure(figsize=(20, 10))\n\nfor i in range(16):\n ax = plt.subplot(4, 4, i + 1)\n image_path = image_file[i]\n image = load_dicom(image_path)\n plt.axis('off') \n plt.imshow(image)","metadata":{"execution":{"iopub.status.busy":"2023-01-07T08:52:12.12016Z","iopub.execute_input":"2023-01-07T08:52:12.120553Z","iopub.status.idle":"2023-01-07T08:52:13.710268Z","shell.execute_reply.started":"2023-01-07T08:52:12.120516Z","shell.execute_reply":"2023-01-07T08:52:13.709352Z"},"trusted":true},"execution_count":4,"outputs":[{"output_type":"display_data","data":{"text/plain":"
","image/png":"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\n"},"metadata":{"needs_background":"light"}}]},{"cell_type":"markdown","source":"#### Create Data Generator\n(As data is so large that it can't fit in memory)","metadata":{}},{"cell_type":"code","source":"def RSNATrainGenerator(train_df, batch_size, infinite = True, base_path = train_images_dir):\n while True:\n trainset = []\n trainidt = []\n trainlabel = []\n for i in (range(len(train_df))):\n idt = train_df.loc[i, 'StudyInstanceUID']\n path = os.path.join(base_path, idt)\n for im in os.listdir(path):\n dc = dicom.read_file(os.path.join(path,im))\n if dc.file_meta.TransferSyntaxUID.name =='JPEG Lossless, Non-Hierarchical, First-Order Prediction (Process 14 [Selection Value 1])':\n continue\n img = load_dicom(os.path.join(path , im))\n img = cv2.resize(img, (128 , 128))\n image = img_to_array(img)\n image = image / 255.0\n trainset += [image]\n cur_label = [train_df.loc[i,f'C{j}'] for j in range(1,8)]\n trainlabel += [cur_label]\n trainidt += [idt]\n if len(trainidt) == batch_size: \n yield np.array(trainset), np.array(trainlabel)\n trainset, trainlabel, trainidt = [], [], []\n i+=1","metadata":{"execution":{"iopub.status.busy":"2023-01-07T08:52:17.289927Z","iopub.execute_input":"2023-01-07T08:52:17.290297Z","iopub.status.idle":"2023-01-07T08:52:17.30285Z","shell.execute_reply.started":"2023-01-07T08:52:17.290265Z","shell.execute_reply":"2023-01-07T08:52:17.3018Z"},"trusted":true},"execution_count":5,"outputs":[]},{"cell_type":"code","source":"def RSNATestGenerator(test_df, batch_size, infinite = True, base_path = test_images_dir):\n while 1: \n testset=[]\n testidt=[]\n for i in (range(len(test_df))): \n if type(test_df) is list: idt = test_df[i]\n else: idt = test_df['StudyInstanceUID'].iloc[i]\n path = os.path.join(base_path, idt)\n if os.path.exists(path):\n for im in os.listdir(path):\n dc = dicom.read_file(os.path.join(path,im))\n if dc.file_meta.TransferSyntaxUID.name =='JPEG Lossless, Non-Hierarchical, First-Order Prediction (Process 14 [Selection Value 1])':\n continue\n img=load_dicom(os.path.join(path,im))\n img=cv2.resize(img,(128, 128))\n image=img_to_array(img)\n image=image/255.0\n testset+=[image]\n testidt+=[idt]\n if len(testset) == batch_size: \n yield np.array(testset)\n testset = []\n if len(testset) > 0: yield np.array(testset)\n if not infinite: break","metadata":{"execution":{"iopub.status.busy":"2023-01-07T08:52:18.966067Z","iopub.execute_input":"2023-01-07T08:52:18.966461Z","iopub.status.idle":"2023-01-07T08:52:18.975521Z","shell.execute_reply.started":"2023-01-07T08:52:18.96642Z","shell.execute_reply":"2023-01-07T08:52:18.974345Z"},"trusted":true},"execution_count":6,"outputs":[]},{"cell_type":"code","source":"train_data = RSNATrainGenerator(df_train, 64)\nsample = next(train_data)\nprint(\"input_shape:\", sample[0].shape)\nprint(\"target_shape:\", sample[1].shape)","metadata":{"execution":{"iopub.status.busy":"2023-01-07T08:52:20.241508Z","iopub.execute_input":"2023-01-07T08:52:20.241884Z","iopub.status.idle":"2023-01-07T08:52:23.360081Z","shell.execute_reply.started":"2023-01-07T08:52:20.241851Z","shell.execute_reply":"2023-01-07T08:52:23.359095Z"},"trusted":true},"execution_count":7,"outputs":[{"name":"stdout","text":"input_shape: (64, 128, 128, 3)\ntarget_shape: (64, 7)\n","output_type":"stream"}]},{"cell_type":"markdown","source":"## Create Model","metadata":{"execution":{"iopub.status.busy":"2022-12-24T08:45:28.342629Z","iopub.execute_input":"2022-12-24T08:45:28.342996Z","iopub.status.idle":"2022-12-24T08:45:28.347812Z","shell.execute_reply.started":"2022-12-24T08:45:28.342963Z","shell.execute_reply":"2022-12-24T08:45:28.346634Z"}}},{"cell_type":"code","source":"def get_model_A1(): \n eff_model = tf.keras.applications.EfficientNetB0(\n include_top=False,\n weights=\"imagenet\",\n pooling=\"max\")\n \n for layer in eff_model.layers[:-10]:\n layer.trainable = False\n \n \n inp = tfl.Input((128, 128 ,3))\n x = eff_model(inp)\n x = tfl.Dense(128, 'relu')(x)\n x = tfl.Dropout(0.5)(x)\n out = tfl.Dense(7, 'sigmoid')(x)\n model = tf.keras.models.Model(inp, out)\n model.compile(loss=\"binary_crossentropy\", optimizer = tf.keras.optimizers.Adam(learning_rate = 0.0001),\n metrics=[tf.keras.metrics.BinaryAccuracy()])\n model.summary()\n return model\n\nget_model_A1()","metadata":{"execution":{"iopub.status.busy":"2023-01-07T08:52:35.383548Z","iopub.execute_input":"2023-01-07T08:52:35.383919Z","iopub.status.idle":"2023-01-07T08:52:41.961822Z","shell.execute_reply.started":"2023-01-07T08:52:35.383889Z","shell.execute_reply":"2023-01-07T08:52:41.960824Z"},"trusted":true},"execution_count":8,"outputs":[{"name":"stderr","text":"2023-01-07 08:52:35.481426: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero\n2023-01-07 08:52:35.677260: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero\n2023-01-07 08:52:35.678169: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero\n2023-01-07 08:52:35.679600: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 AVX512F FMA\nTo enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.\n2023-01-07 08:52:35.679922: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero\n2023-01-07 08:52:35.680633: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero\n2023-01-07 08:52:35.681246: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero\n2023-01-07 08:52:37.846268: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero\n2023-01-07 08:52:37.847273: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero\n2023-01-07 08:52:37.847940: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero\n2023-01-07 08:52:37.848538: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1510] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 15401 MB memory: -> device: 0, name: Tesla P100-PCIE-16GB, pci bus id: 0000:00:04.0, compute capability: 6.0\n","output_type":"stream"},{"name":"stdout","text":"Downloading data from https://storage.googleapis.com/keras-applications/efficientnetb0_notop.h5\n16711680/16705208 [==============================] - 1s 0us/step\n16719872/16705208 [==============================] - 1s 0us/step\nModel: \"model\"\n_________________________________________________________________\nLayer (type) Output Shape Param # \n=================================================================\ninput_2 (InputLayer) [(None, 128, 128, 3)] 0 \n_________________________________________________________________\nefficientnetb0 (Functional) (None, 1280) 4049571 \n_________________________________________________________________\ndense (Dense) (None, 128) 163968 \n_________________________________________________________________\ndropout (Dropout) (None, 128) 0 \n_________________________________________________________________\ndense_1 (Dense) (None, 7) 903 \n=================================================================\nTotal params: 4,214,442\nTrainable params: 1,058,103\nNon-trainable params: 3,156,339\n_________________________________________________________________\n","output_type":"stream"},{"execution_count":8,"output_type":"execute_result","data":{"text/plain":""},"metadata":{}}]},{"cell_type":"code","source":"def get_model_A2():\n inp = tfl.Input((128, 128 ,3))\n x = tfl.Conv2D(32, (3, 3), activation='relu')(inp)\n x = tfl.MaxPooling2D((2, 2))(x)\n x = tfl.Conv2D(64, (3, 3), activation='relu')(inp)\n x = tfl.MaxPooling2D((2, 2))(x)\n x = tfl.Conv2D(128, (3, 3), activation='relu')(inp)\n x = tfl.MaxPooling2D((2, 2))(x)\n x = tfl.Flatten()(x)\n x = tfl.Dense(128, 'relu')(x)\n x = tfl.Dropout(0.5)(x)\n out = tfl.Dense(7, 'sigmoid')(x)\n \n model = tf.keras.models.Model(inp, out)\n \n model.layers[2].trainable = False\n \n model.compile(loss=\"binary_crossentropy\",\n optimizer = tf.keras.optimizers.Adam(learning_rate = 1e-4),\n metrics=[tf.keras.metrics.BinaryAccuracy()])\n model.summary()\n \n return model\n\nget_model_A2()","metadata":{"execution":{"iopub.status.busy":"2023-01-07T08:52:44.215931Z","iopub.execute_input":"2023-01-07T08:52:44.216307Z","iopub.status.idle":"2023-01-07T08:52:44.285778Z","shell.execute_reply.started":"2023-01-07T08:52:44.216267Z","shell.execute_reply":"2023-01-07T08:52:44.284749Z"},"trusted":true},"execution_count":9,"outputs":[{"name":"stdout","text":"Model: \"model_1\"\n_________________________________________________________________\nLayer (type) Output Shape Param # \n=================================================================\ninput_3 (InputLayer) [(None, 128, 128, 3)] 0 \n_________________________________________________________________\nconv2d_2 (Conv2D) (None, 126, 126, 128) 3584 \n_________________________________________________________________\nmax_pooling2d_2 (MaxPooling2 (None, 63, 63, 128) 0 \n_________________________________________________________________\nflatten (Flatten) (None, 508032) 0 \n_________________________________________________________________\ndense_2 (Dense) (None, 128) 65028224 \n_________________________________________________________________\ndropout_1 (Dropout) (None, 128) 0 \n_________________________________________________________________\ndense_3 (Dense) (None, 7) 903 \n=================================================================\nTotal params: 65,032,711\nTrainable params: 65,032,711\nNon-trainable params: 0\n_________________________________________________________________\n","output_type":"stream"},{"execution_count":9,"output_type":"execute_result","data":{"text/plain":""},"metadata":{}}]},{"cell_type":"code","source":"def get_model_M1(): \n MobileNet_model = tf.keras.applications.MobileNet(\n include_top=False,\n weights='imagenet',\n pooling=\"max\",\n)\n \n for layer in MobileNet_model.layers[:-10]:\n layer.trainable = False\n \n \n inp = tfl.Input((128, 128 ,3))\n x = MobileNet_model(inp)\n out = tfl.Dense(7, 'sigmoid')(x)\n model = tf.keras.models.Model(inp, out)\n model.compile(loss=\"binary_crossentropy\", optimizer = tf.keras.optimizers.Adam(learning_rate = 0.0001),\n metrics=[tf.keras.metrics.BinaryAccuracy()])\n model.summary()\n return model","metadata":{"execution":{"iopub.status.busy":"2023-01-07T08:52:45.318535Z","iopub.execute_input":"2023-01-07T08:52:45.319663Z","iopub.status.idle":"2023-01-07T08:52:45.327045Z","shell.execute_reply.started":"2023-01-07T08:52:45.319619Z","shell.execute_reply":"2023-01-07T08:52:45.325861Z"},"trusted":true},"execution_count":10,"outputs":[]},{"cell_type":"code","source":"def get_model_M2():\n DenseNet_model = tf.keras.applications.DenseNet121(\n include_top=False,\n weights='imagenet',\n pooling=\"max\",\n)\n \n for layer in DenseNet_model.layers[:-10]:\n layer.trainable = False\n \n \n inp = tfl.Input((128, 128 ,3))\n x = DenseNet_model(inp)\n out = tfl.Dense(7, 'sigmoid')(x)\n model = tf.keras.models.Model(inp, out)\n model.compile(loss=\"binary_crossentropy\", optimizer = tf.keras.optimizers.Adam(learning_rate = 0.0001),\n metrics=[tf.keras.metrics.BinaryAccuracy()])\n model.summary()\n return model","metadata":{"execution":{"iopub.status.busy":"2023-01-07T08:52:45.955847Z","iopub.execute_input":"2023-01-07T08:52:45.956214Z","iopub.status.idle":"2023-01-07T08:52:45.966702Z","shell.execute_reply.started":"2023-01-07T08:52:45.956181Z","shell.execute_reply":"2023-01-07T08:52:45.965716Z"},"trusted":true},"execution_count":11,"outputs":[]},{"cell_type":"code","source":"def get_model_O1(): \n eff_model = tf.keras.applications.Xception(\n include_top=False,\n weights=\"imagenet\",\n pooling=\"max\"\n )\n \n for layer in eff_model.layers[:-10]:\n layer.trainable = False\n \n \n inp = tfl.Input((128, 128 ,3))\n x = eff_model(inp)\n out = tfl.Dense(7, 'sigmoid')(x)\n model = tf.keras.models.Model(inp, out)\n model.compile(loss=\"binary_crossentropy\", optimizer = tf.keras.optimizers.Adam(learning_rate = 0.0001),\n metrics=[tf.keras.metrics.BinaryAccuracy()])\n model.summary()\n return model","metadata":{"execution":{"iopub.status.busy":"2023-01-07T08:52:50.719132Z","iopub.execute_input":"2023-01-07T08:52:50.719524Z","iopub.status.idle":"2023-01-07T08:52:50.727008Z","shell.execute_reply.started":"2023-01-07T08:52:50.71949Z","shell.execute_reply":"2023-01-07T08:52:50.725647Z"},"trusted":true},"execution_count":12,"outputs":[]},{"cell_type":"code","source":"from tensorflow import keras\nfrom tensorflow.keras import layers\ndef get_model_O2():\n model = keras.Sequential([\n layers.Dense(128, activation='relu', input_shape=[128,128,3]),\n layers.Dropout(0.4),\n layers.Dense(128, activation='relu'),\n layers.Dropout(0.6),\n layers.Dense(64, activation='relu'),\n layers.Flatten(),\n layers.Dense(7, activation='sigmoid'),\n ])\n \n model.compile(loss=\"binary_crossentropy\", optimizer = tf.keras.optimizers.Adam(learning_rate = 1e-4),\n metrics=[tf.keras.metrics.BinaryAccuracy()])\n model.summary()\n \n return model","metadata":{"execution":{"iopub.status.busy":"2023-01-07T08:52:51.34604Z","iopub.execute_input":"2023-01-07T08:52:51.346431Z","iopub.status.idle":"2023-01-07T08:52:51.354066Z","shell.execute_reply.started":"2023-01-07T08:52:51.346374Z","shell.execute_reply":"2023-01-07T08:52:51.353071Z"},"trusted":true},"execution_count":13,"outputs":[]},{"cell_type":"code","source":"def get_model_K1(): \n eff_model = tf.keras.applications.InceptionV3(\n include_top=False,\n weights=\"imagenet\",\n pooling=\"max\"\n )\n \n for layer in eff_model.layers[:-10]:\n layer.trainable = False\n \n \n inp = tfl.Input((128, 128 ,3))\n x = eff_model(inp)\n # x = tfl.Conv2D(3, 3, padding = 'SAME')(x)\n out = tfl.Dense(7, 'sigmoid')(x)\n model = tf.keras.models.Model(inp, out)\n model.layers[2].trainable = False\n model.compile(loss=\"binary_crossentropy\", optimizer = tf.keras.optimizers.Adam(learning_rate = 0.0001),\n metrics=[tf.keras.metrics.BinaryAccuracy()])\n model.summary()\n return model","metadata":{"execution":{"iopub.status.busy":"2023-01-07T08:52:52.287832Z","iopub.execute_input":"2023-01-07T08:52:52.289732Z","iopub.status.idle":"2023-01-07T08:52:52.29813Z","shell.execute_reply.started":"2023-01-07T08:52:52.28968Z","shell.execute_reply":"2023-01-07T08:52:52.296843Z"},"trusted":true},"execution_count":14,"outputs":[]},{"cell_type":"code","source":"def get_model_K2():\n num_classes = 7\n image_size = 128\n model = keras.Sequential([\n layers.experimental.preprocessing.Rescaling(1./255, input_shape=(image_size, image_size, 3)),\n layers.Conv2D(16, 3, padding='same', activation='relu'),\n layers.MaxPooling2D(),\n layers.Conv2D(32, 3, padding='same', activation='relu'),\n layers.MaxPooling2D(),\n layers.Conv2D(64, 3, padding='same', activation='relu'),\n layers.MaxPooling2D(),\n layers.Flatten(),\n layers.Dense(128, activation='relu'),\n layers.Dense(64, activation='relu'),\n layers.Dense(num_classes)])\n model.compile(loss=\"binary_crossentropy\", optimizer = tf.keras.optimizers.Adam(learning_rate = 1e-4),\n metrics=[tf.keras.metrics.BinaryAccuracy()])\n model.summary()\n \n return model","metadata":{"execution":{"iopub.status.busy":"2023-01-07T08:52:53.399852Z","iopub.execute_input":"2023-01-07T08:52:53.400262Z","iopub.status.idle":"2023-01-07T08:52:53.408305Z","shell.execute_reply.started":"2023-01-07T08:52:53.400229Z","shell.execute_reply":"2023-01-07T08:52:53.407055Z"},"trusted":true},"execution_count":15,"outputs":[]},{"cell_type":"code","source":"def get_model_N1():\n base_model = keras.applications.ResNet50(\n weights='imagenet', # Load weights pre-trained on ImageNet.\n input_shape=(128, 128, 3),\n include_top=False) # include the ImageNet classifier at the top.\n base_model.trainable = False\n\n model = tf.keras.models.Sequential()\n model.add(base_model)\n model.add(tf.keras.layers.Flatten())\n# model.add(tf.keras.layers.Dropout(0.5))\n model.add(tf.keras.layers.Dense(128, activation='relu'))\n model.add(tf.keras.layers.Dense(64, activation='relu'))\n model.add(tf.keras.layers.Dense(32, activation='relu'))\n model.add(tf.keras.layers.Dense(1, activation='sigmoid'))\n\n# model.layers[0].trainable = False\n \n model.compile(\n loss='binary_crossentropy',\n optimizer=tf.keras.optimizers.Adam(learning_rate = 1e-4),\n metrics=[tf.keras.metrics.BinaryAccuracy()]\n )\n return model","metadata":{"execution":{"iopub.status.busy":"2023-01-07T08:52:54.442172Z","iopub.execute_input":"2023-01-07T08:52:54.442891Z","iopub.status.idle":"2023-01-07T08:52:54.451183Z","shell.execute_reply.started":"2023-01-07T08:52:54.442852Z","shell.execute_reply":"2023-01-07T08:52:54.44998Z"},"trusted":true},"execution_count":16,"outputs":[]},{"cell_type":"code","source":"def get_model_N2():\n base_model = keras.applications.VGG16(\n weights='imagenet', # Load weights pre-trained on ImageNet.\n input_shape=(128, 128, 3),\n include_top=False) # Do not include the ImageNet classifier at the top.\n base_model.trainable = False\n\n model = tf.keras.models.Sequential()\n model.add(base_model)\n model.add(tf.keras.layers.Flatten())\n# model.add(tf.keras.layers.Dropout(0.5))\n model.add(tf.keras.layers.Dense(128, activation='relu'))\n model.add(tf.keras.layers.Dense(64, activation='relu'))\n model.add(tf.keras.layers.Dense(32, activation='relu'))\n model.add(tf.keras.layers.Dense(1, activation='sigmoid'))\n\n# model.layers[0].trainable = False\n \n model.compile(\n loss='binary_crossentropy',\n optimizer=tf.keras.optimizers.Adam(learning_rate = 1e-4),\n metrics=[tf.keras.metrics.BinaryAccuracy()]\n )\n return model","metadata":{"execution":{"iopub.status.busy":"2023-01-07T08:52:55.51379Z","iopub.execute_input":"2023-01-07T08:52:55.514192Z","iopub.status.idle":"2023-01-07T08:52:55.525571Z","shell.execute_reply.started":"2023-01-07T08:52:55.514159Z","shell.execute_reply":"2023-01-07T08:52:55.524466Z"},"trusted":true},"execution_count":17,"outputs":[]},{"cell_type":"code","source":"functions = [('Abdallah', get_model_A1, get_model_A2), ('Mohammad', get_model_M1, get_model_M2), ('Omar Ahmed', get_model_O1, get_model_O2), ('Omar Khaled', get_model_K1, get_model_K2), ('Nadeen', get_model_N1, get_model_N2)]","metadata":{"execution":{"iopub.status.busy":"2023-01-07T08:52:56.738363Z","iopub.execute_input":"2023-01-07T08:52:56.739099Z","iopub.status.idle":"2023-01-07T08:52:56.74463Z","shell.execute_reply.started":"2023-01-07T08:52:56.739061Z","shell.execute_reply":"2023-01-07T08:52:56.743546Z"},"trusted":true},"execution_count":18,"outputs":[]},{"cell_type":"code","source":"accuracies = []\nfor person in functions:\n print(person[0])\n for train_idx, val_idx in StratifiedKFold(5).split(df_train, df_train['patient_overall']): \n K.clear_session()\n x_train = df_train.iloc[train_idx].reset_index()\n x_val = df_train.iloc[val_idx].reset_index()\n\n train_gen = RSNATrainGenerator(x_train, min(len(x_train), 64), infinite = False, base_path = train_images_dir)\n val_gen = RSNATrainGenerator(x_val, min(len(x_val), 64), infinite = False, base_path = train_images_dir)\n\n model1 = person[1]()\n model2 = person[2]()\n\n\n hist1 = model1.fit_generator( \n train_gen,\n epochs = 5,\n callbacks = [tf.keras.callbacks.EarlyStopping(monitor = 'val_loss', patience = 2, restore_best_weights = True)],\n validation_steps = max((len(x_val) // 64), 1),\n steps_per_epoch = max((len(x_train) // 64), 1),\n validation_data = val_gen,\n )\n\n hist2 = model2.fit_generator( \n train_gen,\n epochs = 5,\n callbacks = [tf.keras.callbacks.EarlyStopping(monitor = 'val_loss', patience = 2, restore_best_weights = True)],\n validation_steps = max((len(x_val) // 64), 1),\n steps_per_epoch = max((len(x_train) // 64), 1),\n validation_data = val_gen,\n )\n accuracies.append(model1.evaluate(val_gen, steps = max((len(x_val) // 64), 1))[1])\n accuracies.append(model2.evaluate(val_gen, steps = max((len(x_val) // 64), 1))[1])\n try: # the best we can do at the moment..\n preds1 = model1.predict_generator(RSNATestGenerator(df_test, min(len(df_test), 64), infinite = False, base_path = test_images_dir), steps = max((len(df_test) // 64), 1))\n preds2 = model2.predict_generator(RSNATestGenerator(df_test, min(len(df_test), 64), infinite = False, base_path = test_images_dir), steps = max((len(df_test) // 64), 1))\n\n new_preds = []\n for pred_idx in range(len(preds1)):\n new_preds.append(preds1[pred_idx][prediction_type_mapping[pred_idx]])\n submission['fractured'] += np.array(new_preds) / 10\n\n new_preds = []\n for pred_idx in range(len(preds2)):\n new_preds.append(preds2[pred_idx][prediction_type_mapping[pred_idx]])\n submission['fractured'] += np.array(new_preds) / 10\n\n except: traceback.print_exc() ","metadata":{"execution":{"iopub.status.busy":"2023-01-07T08:52:57.433748Z","iopub.execute_input":"2023-01-07T08:52:57.434753Z"},"trusted":true},"execution_count":null,"outputs":[{"name":"stdout","text":"Abdallah\nModel: \"model\"\n_________________________________________________________________\nLayer (type) Output Shape Param # \n=================================================================\ninput_2 (InputLayer) [(None, 128, 128, 3)] 0 \n_________________________________________________________________\nefficientnetb0 (Functional) (None, 1280) 4049571 \n_________________________________________________________________\ndense (Dense) (None, 128) 163968 \n_________________________________________________________________\ndropout (Dropout) (None, 128) 0 \n_________________________________________________________________\ndense_1 (Dense) (None, 7) 903 \n=================================================================\nTotal params: 4,214,442\nTrainable params: 1,058,103\nNon-trainable params: 3,156,339\n_________________________________________________________________\nModel: \"model_1\"\n_________________________________________________________________\nLayer (type) Output Shape Param # \n=================================================================\ninput_3 (InputLayer) [(None, 128, 128, 3)] 0 \n_________________________________________________________________\nconv2d_2 (Conv2D) (None, 126, 126, 128) 3584 \n_________________________________________________________________\nmax_pooling2d_2 (MaxPooling2 (None, 63, 63, 128) 0 \n_________________________________________________________________\nflatten (Flatten) (None, 508032) 0 \n_________________________________________________________________\ndense_2 (Dense) (None, 128) 65028224 \n_________________________________________________________________\ndropout_1 (Dropout) (None, 128) 0 \n_________________________________________________________________\ndense_3 (Dense) (None, 7) 903 \n=================================================================\nTotal params: 65,032,711\nTrainable params: 65,032,711\nNon-trainable params: 0\n_________________________________________________________________\n","output_type":"stream"},{"name":"stderr","text":"/opt/conda/lib/python3.7/site-packages/keras/engine/training.py:1972: UserWarning: `Model.fit_generator` is deprecated and will be removed in a future version. Please use `Model.fit`, which supports generators.\n warnings.warn('`Model.fit_generator` is deprecated and '\n2023-01-07 08:53:00.993744: I tensorflow/compiler/mlir/mlir_graph_optimization_pass.cc:185] None of the MLIR Optimization Passes are enabled (registered 2)\n","output_type":"stream"},{"name":"stdout","text":"Epoch 1/5\n","output_type":"stream"},{"name":"stderr","text":"2023-01-07 08:53:07.277891: I tensorflow/stream_executor/cuda/cuda_dnn.cc:369] Loaded cuDNN version 8005\n","output_type":"stream"},{"name":"stdout","text":"25/25 [==============================] - 43s 1s/step - loss: 0.4451 - binary_accuracy: 0.8954 - val_loss: 0.5055 - val_binary_accuracy: 0.8571\nEpoch 2/5\n25/25 [==============================] - 39s 2s/step - loss: 0.4122 - binary_accuracy: 0.9316 - val_loss: 0.6716 - val_binary_accuracy: 0.8571\nEpoch 3/5\n25/25 [==============================] - 31s 1s/step - loss: 1.8133 - binary_accuracy: 0.7472 - val_loss: 0.6774 - val_binary_accuracy: 0.6443\nEpoch 1/5\n25/25 [==============================] - 31s 1s/step - loss: 1.6781 - binary_accuracy: 0.8470 - val_loss: 2.3982 - val_binary_accuracy: 0.7143\nEpoch 2/5\n25/25 [==============================] - 31s 1s/step - loss: 2.1060 - binary_accuracy: 0.7629 - val_loss: 1.0162 - val_binary_accuracy: 0.8571\nEpoch 3/5\n25/25 [==============================] - 30s 1s/step - loss: 1.1673 - binary_accuracy: 0.5680 - val_loss: 0.3883 - val_binary_accuracy: 0.9048\nEpoch 4/5\n25/25 [==============================] - 39s 2s/step - loss: 0.5275 - binary_accuracy: 0.7724 - val_loss: 0.3686 - val_binary_accuracy: 0.9762\nEpoch 5/5\n25/25 [==============================] - 31s 1s/step - loss: 0.4809 - binary_accuracy: 0.8025 - val_loss: 0.8676 - val_binary_accuracy: 0.6455\n6/6 [==============================] - 5s 1s/step - loss: 0.0209 - binary_accuracy: 1.0000\n6/6 [==============================] - 6s 1s/step - loss: 0.3963 - binary_accuracy: 0.9639\n","output_type":"stream"},{"name":"stderr","text":"/opt/conda/lib/python3.7/site-packages/keras/engine/training.py:2035: UserWarning: `Model.predict_generator` is deprecated and will be removed in a future version. Please use `Model.predict`, which supports generators.\n warnings.warn('`Model.predict_generator` is deprecated and '\n","output_type":"stream"},{"name":"stdout","text":"Model: \"model\"\n_________________________________________________________________\nLayer (type) Output Shape Param # \n=================================================================\ninput_2 (InputLayer) [(None, 128, 128, 3)] 0 \n_________________________________________________________________\nefficientnetb0 (Functional) (None, 1280) 4049571 \n_________________________________________________________________\ndense (Dense) (None, 128) 163968 \n_________________________________________________________________\ndropout (Dropout) (None, 128) 0 \n_________________________________________________________________\ndense_1 (Dense) (None, 7) 903 \n=================================================================\nTotal params: 4,214,442\nTrainable params: 1,058,103\nNon-trainable params: 3,156,339\n_________________________________________________________________\nModel: \"model_1\"\n_________________________________________________________________\nLayer (type) Output Shape Param # \n=================================================================\ninput_3 (InputLayer) [(None, 128, 128, 3)] 0 \n_________________________________________________________________\nconv2d_2 (Conv2D) (None, 126, 126, 128) 3584 \n_________________________________________________________________\nmax_pooling2d_2 (MaxPooling2 (None, 63, 63, 128) 0 \n_________________________________________________________________\nflatten (Flatten) (None, 508032) 0 \n_________________________________________________________________\ndense_2 (Dense) (None, 128) 65028224 \n_________________________________________________________________\ndropout_1 (Dropout) (None, 128) 0 \n_________________________________________________________________\ndense_3 (Dense) (None, 7) 903 \n=================================================================\nTotal params: 65,032,711\nTrainable params: 65,032,711\nNon-trainable params: 0\n_________________________________________________________________\nEpoch 1/5\n25/25 [==============================] - 34s 1s/step - loss: 1.5179 - binary_accuracy: 0.7677 - val_loss: 0.1777 - val_binary_accuracy: 1.0000\nEpoch 2/5\n25/25 [==============================] - 18s 752ms/step - loss: 0.5175 - binary_accuracy: 0.8584 - val_loss: 0.2614 - val_binary_accuracy: 0.8571\nEpoch 3/5\n25/25 [==============================] - 19s 789ms/step - loss: 0.6886 - binary_accuracy: 0.8080 - val_loss: 0.4439 - val_binary_accuracy: 0.8571\nEpoch 1/5\n25/25 [==============================] - 34s 1s/step - loss: 1.2024 - binary_accuracy: 0.7683 - val_loss: 0.0266 - val_binary_accuracy: 1.0000\nEpoch 2/5\n25/25 [==============================] - 40s 2s/step - loss: 1.3510 - binary_accuracy: 0.7169 - val_loss: 0.4570 - val_binary_accuracy: 0.6923\nEpoch 3/5\n25/25 [==============================] - 35s 1s/step - loss: 0.5926 - binary_accuracy: 0.7273 - val_loss: 0.4542 - val_binary_accuracy: 0.8251\n6/6 [==============================] - 5s 908ms/step - loss: 0.1778 - binary_accuracy: 1.0000\n6/6 [==============================] - 4s 806ms/step - loss: 0.2654 - binary_accuracy: 0.9100\nModel: \"model\"\n_________________________________________________________________\nLayer (type) Output Shape Param # \n=================================================================\ninput_2 (InputLayer) [(None, 128, 128, 3)] 0 \n_________________________________________________________________\nefficientnetb0 (Functional) (None, 1280) 4049571 \n_________________________________________________________________\ndense (Dense) (None, 128) 163968 \n_________________________________________________________________\ndropout (Dropout) (None, 128) 0 \n_________________________________________________________________\ndense_1 (Dense) (None, 7) 903 \n=================================================================\nTotal params: 4,214,442\nTrainable params: 1,058,103\nNon-trainable params: 3,156,339\n_________________________________________________________________\nModel: \"model_1\"\n_________________________________________________________________\nLayer (type) Output Shape Param # \n=================================================================\ninput_3 (InputLayer) [(None, 128, 128, 3)] 0 \n_________________________________________________________________\nconv2d_2 (Conv2D) (None, 126, 126, 128) 3584 \n_________________________________________________________________\nmax_pooling2d_2 (MaxPooling2 (None, 63, 63, 128) 0 \n_________________________________________________________________\nflatten (Flatten) (None, 508032) 0 \n_________________________________________________________________\ndense_2 (Dense) (None, 128) 65028224 \n_________________________________________________________________\ndropout_1 (Dropout) (None, 128) 0 \n_________________________________________________________________\ndense_3 (Dense) (None, 7) 903 \n=================================================================\nTotal params: 65,032,711\nTrainable params: 65,032,711\nNon-trainable params: 0\n_________________________________________________________________\nEpoch 1/5\n25/25 [==============================] - 41s 1s/step - loss: 1.7639 - binary_accuracy: 0.8035 - val_loss: 0.3386 - val_binary_accuracy: 1.0000\nEpoch 2/5\n25/25 [==============================] - 25s 1s/step - loss: 0.5231 - binary_accuracy: 0.8579 - val_loss: 0.3932 - val_binary_accuracy: 0.8571\nEpoch 3/5\n25/25 [==============================] - 24s 1s/step - loss: 0.6785 - binary_accuracy: 0.8062 - val_loss: 0.4891 - val_binary_accuracy: 1.0000\nEpoch 1/5\n25/25 [==============================] - 26s 1s/step - loss: 1.2368 - binary_accuracy: 0.7956 - val_loss: 0.0275 - val_binary_accuracy: 1.0000\nEpoch 2/5\n25/25 [==============================] - 26s 1s/step - loss: 1.3613 - binary_accuracy: 0.7520 - val_loss: 1.5565 - val_binary_accuracy: 0.7143\nEpoch 3/5\n25/25 [==============================] - 34s 1s/step - loss: 1.0025 - binary_accuracy: 0.6821 - val_loss: 0.4623 - val_binary_accuracy: 0.8571\n6/6 [==============================] - 5s 1s/step - loss: 0.3387 - binary_accuracy: 1.0000\n6/6 [==============================] - 5s 1s/step - loss: 0.0196 - binary_accuracy: 1.0000\nModel: \"model\"\n_________________________________________________________________\nLayer (type) Output Shape Param # \n=================================================================\ninput_2 (InputLayer) [(None, 128, 128, 3)] 0 \n_________________________________________________________________\nefficientnetb0 (Functional) (None, 1280) 4049571 \n_________________________________________________________________\ndense (Dense) (None, 128) 163968 \n_________________________________________________________________\ndropout (Dropout) (None, 128) 0 \n_________________________________________________________________\ndense_1 (Dense) (None, 7) 903 \n=================================================================\nTotal params: 4,214,442\nTrainable params: 1,058,103\nNon-trainable params: 3,156,339\n_________________________________________________________________\nModel: \"model_1\"\n_________________________________________________________________\nLayer (type) Output Shape Param # \n=================================================================\ninput_3 (InputLayer) [(None, 128, 128, 3)] 0 \n_________________________________________________________________\nconv2d_2 (Conv2D) (None, 126, 126, 128) 3584 \n_________________________________________________________________\nmax_pooling2d_2 (MaxPooling2 (None, 63, 63, 128) 0 \n_________________________________________________________________\nflatten (Flatten) (None, 508032) 0 \n_________________________________________________________________\ndense_2 (Dense) (None, 128) 65028224 \n_________________________________________________________________\ndropout_1 (Dropout) (None, 128) 0 \n_________________________________________________________________\ndense_3 (Dense) (None, 7) 903 \n=================================================================\nTotal params: 65,032,711\nTrainable params: 65,032,711\nNon-trainable params: 0\n_________________________________________________________________\nEpoch 1/5\n25/25 [==============================] - 25s 809ms/step - loss: 1.9319 - binary_accuracy: 0.6991 - val_loss: 0.2731 - val_binary_accuracy: 1.0000\nEpoch 2/5\n25/25 [==============================] - 23s 955ms/step - loss: 0.6334 - binary_accuracy: 0.8298 - val_loss: 0.3425 - val_binary_accuracy: 0.8571\nEpoch 3/5\n25/25 [==============================] - 27s 1s/step - loss: 0.6561 - binary_accuracy: 0.8122 - val_loss: 0.4414 - val_binary_accuracy: 1.0000\nEpoch 1/5\n25/25 [==============================] - 26s 1s/step - loss: 1.0507 - binary_accuracy: 0.7438 - val_loss: 0.2378 - val_binary_accuracy: 0.8571\nEpoch 2/5\n25/25 [==============================] - 23s 953ms/step - loss: 1.1235 - binary_accuracy: 0.6759 - val_loss: 0.4698 - val_binary_accuracy: 0.8571\nEpoch 3/5\n25/25 [==============================] - 20s 831ms/step - loss: 0.6197 - binary_accuracy: 0.7493 - val_loss: 0.5821 - val_binary_accuracy: 0.8571\n6/6 [==============================] - 5s 964ms/step - loss: 0.2731 - binary_accuracy: 1.0000\n6/6 [==============================] - 5s 973ms/step - loss: 0.2541 - binary_accuracy: 0.8571\nModel: \"model\"\n_________________________________________________________________\nLayer (type) Output Shape Param # \n=================================================================\ninput_2 (InputLayer) [(None, 128, 128, 3)] 0 \n_________________________________________________________________\nefficientnetb0 (Functional) (None, 1280) 4049571 \n_________________________________________________________________\ndense (Dense) (None, 128) 163968 \n_________________________________________________________________\ndropout (Dropout) (None, 128) 0 \n_________________________________________________________________\ndense_1 (Dense) (None, 7) 903 \n=================================================================\nTotal params: 4,214,442\nTrainable params: 1,058,103\nNon-trainable params: 3,156,339\n_________________________________________________________________\nModel: \"model_1\"\n_________________________________________________________________\nLayer (type) Output Shape Param # \n=================================================================\ninput_3 (InputLayer) [(None, 128, 128, 3)] 0 \n_________________________________________________________________\nconv2d_2 (Conv2D) (None, 126, 126, 128) 3584 \n_________________________________________________________________\nmax_pooling2d_2 (MaxPooling2 (None, 63, 63, 128) 0 \n_________________________________________________________________\nflatten (Flatten) (None, 508032) 0 \n_________________________________________________________________\ndense_2 (Dense) (None, 128) 65028224 \n_________________________________________________________________\ndropout_1 (Dropout) (None, 128) 0 \n_________________________________________________________________\ndense_3 (Dense) (None, 7) 903 \n=================================================================\nTotal params: 65,032,711\nTrainable params: 65,032,711\nNon-trainable params: 0\n_________________________________________________________________\nEpoch 1/5\n25/25 [==============================] - 33s 1s/step - loss: 1.9881 - binary_accuracy: 0.7628 - val_loss: 0.5718 - val_binary_accuracy: 0.7574\nEpoch 2/5\n25/25 [==============================] - 25s 1s/step - loss: 0.5767 - binary_accuracy: 0.8706 - val_loss: 0.5904 - val_binary_accuracy: 0.7277\nEpoch 3/5\n25/25 [==============================] - 21s 890ms/step - loss: 0.7973 - binary_accuracy: 0.8149 - val_loss: 0.5855 - val_binary_accuracy: 0.7143\nEpoch 1/5\n25/25 [==============================] - 31s 1s/step - loss: 1.2103 - binary_accuracy: 0.7592 - val_loss: 0.2949 - val_binary_accuracy: 0.9807\nEpoch 2/5\n25/25 [==============================] - 35s 1s/step - loss: 1.6949 - binary_accuracy: 0.7536 - val_loss: 1.4676 - val_binary_accuracy: 0.7143\nEpoch 3/5\n25/25 [==============================] - 39s 2s/step - loss: 1.1008 - binary_accuracy: 0.7029 - val_loss: 0.2398 - val_binary_accuracy: 0.9784\nEpoch 4/5\n25/25 [==============================] - 38s 2s/step - loss: 0.4862 - binary_accuracy: 0.8085 - val_loss: 0.3519 - val_binary_accuracy: 0.9137\nEpoch 5/5\n25/25 [==============================] - 42s 2s/step - loss: 0.2393 - binary_accuracy: 0.9246 - val_loss: 0.0339 - val_binary_accuracy: 1.0000\n6/6 [==============================] - 7s 1s/step - loss: 0.1338 - binary_accuracy: 1.0000\n6/6 [==============================] - 7s 1s/step - loss: 1.1961 - binary_accuracy: 0.7288\nMohammad\nDownloading data from https://storage.googleapis.com/tensorflow/keras-applications/mobilenet/mobilenet_1_0_224_tf_no_top.h5\n17227776/17225924 [==============================] - 1s 0us/step\n17235968/17225924 [==============================] - 1s 0us/step\nModel: \"model\"\n_________________________________________________________________\nLayer (type) Output Shape Param # \n=================================================================\ninput_2 (InputLayer) [(None, 128, 128, 3)] 0 \n_________________________________________________________________\nmobilenet_1.00_224 (Function (None, 1024) 3228864 \n_________________________________________________________________\ndense (Dense) (None, 7) 7175 \n=================================================================\nTotal params: 3,236,039\nTrainable params: 1,595,399\nNon-trainable params: 1,640,640\n_________________________________________________________________\nDownloading data from https://storage.googleapis.com/tensorflow/keras-applications/densenet/densenet121_weights_tf_dim_ordering_tf_kernels_notop.h5\n29089792/29084464 [==============================] - 1s 0us/step\n29097984/29084464 [==============================] - 1s 0us/step\nModel: \"model_1\"\n_________________________________________________________________\nLayer (type) Output Shape Param # \n=================================================================\ninput_4 (InputLayer) [(None, 128, 128, 3)] 0 \n_________________________________________________________________\ndensenet121 (Functional) (None, 1024) 7037504 \n_________________________________________________________________\ndense_1 (Dense) (None, 7) 7175 \n=================================================================\nTotal params: 7,044,679\nTrainable params: 175,303\nNon-trainable params: 6,869,376\n_________________________________________________________________\n","output_type":"stream"},{"name":"stderr","text":"/opt/conda/lib/python3.7/site-packages/keras/engine/training.py:1972: UserWarning: `Model.fit_generator` is deprecated and will be removed in a future version. Please use `Model.fit`, which supports generators.\n warnings.warn('`Model.fit_generator` is deprecated and '\n","output_type":"stream"},{"name":"stdout","text":"Epoch 1/5\n25/25 [==============================] - 31s 1s/step - loss: 0.3001 - binary_accuracy: 0.9113 - val_loss: 1.4625 - val_binary_accuracy: 0.7422\nEpoch 2/5\n25/25 [==============================] - 33s 1s/step - loss: 0.2168 - binary_accuracy: 0.9611 - val_loss: 1.3555 - val_binary_accuracy: 0.6990\nEpoch 3/5\n25/25 [==============================] - 28s 1s/step - loss: 1.3347 - binary_accuracy: 0.8123 - val_loss: 2.0858 - val_binary_accuracy: 0.5513\nEpoch 4/5\n25/25 [==============================] - 29s 1s/step - loss: 0.4812 - binary_accuracy: 0.8648 - val_loss: 0.6968 - val_binary_accuracy: 0.8121\nEpoch 5/5\n25/25 [==============================] - 28s 1s/step - loss: 0.9181 - binary_accuracy: 0.7783 - val_loss: 1.0158 - val_binary_accuracy: 0.8199\nEpoch 1/5\n25/25 [==============================] - 36s 1s/step - loss: 1.1551 - binary_accuracy: 0.5585 - val_loss: 1.1394 - val_binary_accuracy: 0.6629\nEpoch 2/5\n25/25 [==============================] - 34s 1s/step - loss: 0.5538 - binary_accuracy: 0.7781 - val_loss: 0.5176 - val_binary_accuracy: 0.7467\nEpoch 3/5\n25/25 [==============================] - 27s 1s/step - loss: 0.3587 - binary_accuracy: 0.8788 - val_loss: 1.4426 - val_binary_accuracy: 0.5982\nEpoch 4/5\n25/25 [==============================] - 36s 1s/step - loss: 0.3907 - binary_accuracy: 0.8623 - val_loss: 0.3249 - val_binary_accuracy: 0.8612\nEpoch 5/5\n25/25 [==============================] - 35s 1s/step - loss: 0.3259 - binary_accuracy: 0.8748 - val_loss: 0.3989 - val_binary_accuracy: 0.8519\n6/6 [==============================] - 4s 817ms/step - loss: 1.5057 - binary_accuracy: 0.7705\n6/6 [==============================] - 6s 1s/step - loss: 1.0024 - binary_accuracy: 0.6860\n","output_type":"stream"},{"name":"stderr","text":"/opt/conda/lib/python3.7/site-packages/keras/engine/training.py:2035: UserWarning: `Model.predict_generator` is deprecated and will be removed in a future version. Please use `Model.predict`, which supports generators.\n warnings.warn('`Model.predict_generator` is deprecated and '\n","output_type":"stream"},{"name":"stdout","text":"Model: \"model\"\n_________________________________________________________________\nLayer (type) Output Shape Param # \n=================================================================\ninput_2 (InputLayer) [(None, 128, 128, 3)] 0 \n_________________________________________________________________\nmobilenet_1.00_224 (Function (None, 1024) 3228864 \n_________________________________________________________________\ndense (Dense) (None, 7) 7175 \n=================================================================\nTotal params: 3,236,039\nTrainable params: 1,595,399\nNon-trainable params: 1,640,640\n_________________________________________________________________\nModel: \"model_1\"\n_________________________________________________________________\nLayer (type) Output Shape Param # \n=================================================================\ninput_4 (InputLayer) [(None, 128, 128, 3)] 0 \n_________________________________________________________________\ndensenet121 (Functional) (None, 1024) 7037504 \n_________________________________________________________________\ndense_1 (Dense) (None, 7) 7175 \n=================================================================\nTotal params: 7,044,679\nTrainable params: 175,303\nNon-trainable params: 6,869,376\n_________________________________________________________________\nEpoch 1/5\n25/25 [==============================] - 29s 1s/step - loss: 1.1470 - binary_accuracy: 0.6924 - val_loss: 2.5050 - val_binary_accuracy: 0.3754\nEpoch 2/5\n25/25 [==============================] - 21s 872ms/step - loss: 0.4006 - binary_accuracy: 0.8983 - val_loss: 1.4127 - val_binary_accuracy: 0.5398\nEpoch 3/5\n25/25 [==============================] - 24s 989ms/step - loss: 0.6795 - binary_accuracy: 0.8338 - val_loss: 1.2377 - val_binary_accuracy: 0.6220\nEpoch 4/5\n25/25 [==============================] - 27s 1s/step - loss: 0.9202 - binary_accuracy: 0.7991 - val_loss: 0.8399 - val_binary_accuracy: 0.6860\nEpoch 5/5\n25/25 [==============================] - 35s 1s/step - loss: 1.3329 - binary_accuracy: 0.7088 - val_loss: 0.8668 - val_binary_accuracy: 0.7061\nEpoch 1/5\n25/25 [==============================] - 39s 1s/step - loss: 1.2785 - binary_accuracy: 0.5662 - val_loss: 0.8192 - val_binary_accuracy: 0.6685\nEpoch 2/5\n25/25 [==============================] - 30s 1s/step - loss: 0.7468 - binary_accuracy: 0.7086 - val_loss: 0.2497 - val_binary_accuracy: 0.9014\nEpoch 3/5\n25/25 [==============================] - 32s 1s/step - loss: 0.3153 - binary_accuracy: 0.9315 - val_loss: 0.4724 - val_binary_accuracy: 0.8642\nEpoch 4/5\n25/25 [==============================] - 36s 1s/step - loss: 0.4121 - binary_accuracy: 0.8875 - val_loss: 0.7752 - val_binary_accuracy: 0.6823\n6/6 [==============================] - 4s 888ms/step - loss: 0.8116 - binary_accuracy: 0.7135\n6/6 [==============================] - 4s 872ms/step - loss: 0.3380 - binary_accuracy: 0.8423\nModel: \"model\"\n_________________________________________________________________\nLayer (type) Output Shape Param # \n=================================================================\ninput_2 (InputLayer) [(None, 128, 128, 3)] 0 \n_________________________________________________________________\nmobilenet_1.00_224 (Function (None, 1024) 3228864 \n_________________________________________________________________\ndense (Dense) (None, 7) 7175 \n=================================================================\nTotal params: 3,236,039\nTrainable params: 1,595,399\nNon-trainable params: 1,640,640\n_________________________________________________________________\n","output_type":"stream"}]},{"cell_type":"code","source":"np.array(accuracies).mean()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission.to_csv('submission.csv', index = 0)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"new_preds","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"np.array(new_preds) / 5","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}