{"cells":[{"metadata":{},"cell_type":"markdown","source":"## Update 25/11\n\n1. Using 15*TTA\n"},{"metadata":{"trusted":true},"cell_type":"code","source":"## Importing Required Libaries","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import pandas as pd\nimport matplotlib.pyplot as plt\nimport numpy as np\nimport tensorflow as tf\nimport glob\nfrom tensorflow.keras.models import Sequential, Model, load_model\nfrom tensorflow.keras.applications import EfficientNetB3\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom sklearn.model_selection import train_test_split\nfrom tensorflow import keras\n\nSEED = 42\nDEBUG = False\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Loading Best Model"},{"metadata":{"trusted":true},"cell_type":"code","source":"weight_path = '../input/efficientnetb3-keras-tf2-baseline-training/best_model.hdf5'\n\nmy_model = load_model(weight_path)\n\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**While Saving I am saving weights plus architecture so I don't need to build the model again here**"},{"metadata":{},"cell_type":"markdown","source":"## Test Data Generator"},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"\ntest_images = glob.glob('../input/cassava-leaf-disease-classification/test_images/*.jpg')\n\ndf_test = pd.DataFrame(test_images, columns = ['path'])\n\n\n\ndef make_test_gen( batch_size=64):\n    my_test_idg = ImageDataGenerator(#rescale=1. / 255.0,\n                                    horizontal_flip = True, \n                                    vertical_flip = True, \n                                    height_shift_range=0.2, \n                                    width_shift_range=0.2, \n                                    brightness_range=[0.7, 1.5],\n                                    rotation_range=30, \n                                    shear_range=0.2,\n                                    fill_mode='nearest',\n                                    zoom_range=[0.3,0.6])\n        \n    test_gen= my_test_idg.flow_from_dataframe(dataframe=df_test,\n\n                                                x_col=\"path\",\n                                                y_col=None,\n                                                batch_size=batch_size,\n                                                seed=42,\n                                                shuffle=False,\n                                                class_mode=None,\n                                                target_size=(300,300)) ## (height, width)\n    return test_gen\n\n\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_gen = make_test_gen(batch_size = 128)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"preds = []\nfor i in range(15):\n    #test_gen.reset()\n    local_pred = my_model.predict(test_gen,  verbose = True)\n    preds.append(local_pred)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pred_test = np.mean(preds, axis=0)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Generating Predictions"},{"metadata":{"trusted":true},"cell_type":"code","source":"#pred_test = my_model.predict(test_gen,  verbose = True)\npred_test_labels = np.argmax(pred_test, axis = -1)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Generating Predictions File"},{"metadata":{"trusted":true},"cell_type":"code","source":"final_submission = df_test\nfinal_submission['image_id'] = final_submission.path.str.split('/').str[-1]\nfinal_submission['label'] = pred_test_labels\n\nfinal_csv = final_submission[['image_id', 'label']]\nfinal_csv.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"final_csv.to_csv('submission.csv', index=False)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Train Baseline Kernel is [here](https://www.kaggle.com/harveenchadha/efficientnetb3-keras-tf2-baseline-training).\n\n"}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}