{"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_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import numpy as np \nimport pandas as pd\nimport math, re, os\nimport tensorflow as tf\nimport numpy as np\nfrom matplotlib import pyplot as plt\nfrom kaggle_datasets import KaggleDatasets\nfrom sklearn.metrics import f1_score, precision_score, recall_score, confusion_matrix\nprint(\"Tensorflow version \" + tf.__version__)\nAUTO = tf.data.experimental.AUTOTUNE\nimport tensorflow.keras.backend as K","metadata":{"execution":{"iopub.status.busy":"2021-08-12T14:04:21.414078Z","iopub.execute_input":"2021-08-12T14:04:21.414662Z","iopub.status.idle":"2021-08-12T14:04:29.030281Z","shell.execute_reply.started":"2021-08-12T14:04:21.414553Z","shell.execute_reply":"2021-08-12T14:04:29.029124Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Distribution Strategy","metadata":{}},{"cell_type":"code","source":"# Detect hardware, return appropriate distribution strategy\ntry:\n tpu = tf.distribute.cluster_resolver.TPUClusterResolver() # TPU detection. No parameters necessary if TPU_NAME environment variable is set. On Kaggle this is always the case.\n print('Running on TPU ', tpu.master())\nexcept ValueError:\n tpu = None\n\nif tpu:\n tf.config.experimental_connect_to_cluster(tpu)\n tf.tpu.experimental.initialize_tpu_system(tpu)\n strategy = tf.distribute.experimental.TPUStrategy(tpu)\nelse:\n strategy = tf.distribute.get_strategy() # default distribution strategy in Tensorflow. Works on CPU and single GPU.\n\nprint(\"REPLICAS: \", strategy.num_replicas_in_sync)\n\nGCS_DS_PATH = KaggleDatasets().get_gcs_path() # you can list the bucket with \"!gsutil ls $GCS_DS_PATH\"\nprint(GCS_DS_PATH) # what do gcs paths look like?","metadata":{"execution":{"iopub.status.busy":"2021-08-12T14:04:56.126227Z","iopub.execute_input":"2021-08-12T14:04:56.126607Z","iopub.status.idle":"2021-08-12T14:05:04.162348Z","shell.execute_reply.started":"2021-08-12T14:04:56.126572Z","shell.execute_reply":"2021-08-12T14:05:04.161263Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Load Data\n","metadata":{}},{"cell_type":"code","source":"IMAGE_SIZE = [512,512] # At this size, a GPU will run out of memory. Use the TPU.\n # For GPU training, please select 224 x 224 px image size.\nBATCH_SIZE = 16 * strategy.num_replicas_in_sync\n\nGCS_PATH_SELECT = { # available image sizes\n 192: GCS_DS_PATH + '/tfrecords-jpeg-192x192',\n 224: GCS_DS_PATH + '/tfrecords-jpeg-224x224',\n 331: GCS_DS_PATH + '/tfrecords-jpeg-331x331',\n 512: GCS_DS_PATH + '/tfrecords-jpeg-512x512'\n}\nGCS_PATH = GCS_PATH_SELECT[IMAGE_SIZE[0]]\n\nTRAINING_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/train/*.tfrec')\nVALIDATION_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/val/*.tfrec')\nTEST_FILENAMES = tf.io.gfile.glob(GCS_PATH + '/test/*.tfrec') # predictions on this dataset should be submitted for the competition\n\nCLASSES = ['pink primrose', 'hard-leaved pocket orchid', 'canterbury bells', 'sweet pea', 'wild geranium', 'tiger lily', 'moon orchid', 'bird of paradise', 'monkshood', 'globe thistle', # 00 - 09\n 'snapdragon', \"colt's foot\", 'king protea', 'spear thistle', 'yellow iris', 'globe-flower', 'purple coneflower', 'peruvian lily', 'balloon flower', 'giant white arum lily', # 10 - 19\n 'fire lily', 'pincushion flower', 'fritillary', 'red ginger', 'grape hyacinth', 'corn poppy', 'prince of wales feathers', 'stemless gentian', 'artichoke', 'sweet william', # 20 - 29\n 'carnation', 'garden phlox', 'love in the mist', 'cosmos', 'alpine sea holly', 'ruby-lipped cattleya', 'cape flower', 'great masterwort', 'siam tulip', 'lenten rose', # 30 - 39\n 'barberton daisy', 'daffodil', 'sword lily', 'poinsettia', 'bolero deep blue', 'wallflower', 'marigold', 'buttercup', 'daisy', 'common dandelion', # 40 - 49\n 'petunia', 'wild pansy', 'primula', 'sunflower', 'lilac hibiscus', 'bishop of llandaff', 'gaura', 'geranium', 'orange dahlia', 'pink-yellow dahlia', # 50 - 59\n 'cautleya spicata', 'japanese anemone', 'black-eyed susan', 'silverbush', 'californian poppy', 'osteospermum', 'spring crocus', 'iris', 'windflower', 'tree poppy', # 60 - 69\n 'gazania', 'azalea', 'water lily', 'rose', 'thorn apple', 'morning glory', 'passion flower', 'lotus', 'toad lily', 'anthurium', # 70 - 79\n 'frangipani', 'clematis', 'hibiscus', 'columbine', 'desert-rose', 'tree mallow', 'magnolia', 'cyclamen ', 'watercress', 'canna lily', # 80 - 89\n 'hippeastrum ', 'bee balm', 'pink quill', 'foxglove', 'bougainvillea', 'camellia', 'mallow', 'mexican petunia', 'bromelia', 'blanket flower', # 90 - 99\n 'trumpet creeper', 'blackberry lily', 'common tulip', 'wild rose'] # 100 - 102","metadata":{"execution":{"iopub.status.busy":"2021-08-12T14:05:04.163890Z","iopub.execute_input":"2021-08-12T14:05:04.164219Z","iopub.status.idle":"2021-08-12T14:05:04.453224Z","shell.execute_reply.started":"2021-08-12T14:05:04.164181Z","shell.execute_reply":"2021-08-12T14:05:04.452016Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Dataset\n","metadata":{}},{"cell_type":"code","source":"import random\nHEIGHT = 512\nWIDTH = 512\ndef erase(img, max_height=80, max_width=80, min_height=40, min_width=40, img_size=512):\n h, w, c = img_size, img_size, 3\n erase_height = tf.random.uniform(shape=[], minval=min_height, maxval=max_height, dtype=tf.int32)\n erase_width = tf.random.uniform(shape=[], minval=min_width, maxval=max_width, dtype=tf.int32)\n\n erase_area = tf.zeros(shape=[erase_height, erase_width, c])\n erase_area = tf.cast(erase_area, tf.uint8)\n\n pad_h = h - erase_height\n pad_top = tf.random.uniform(shape=[], minval=0, maxval=pad_h, dtype=tf.int32)\n pad_bottom = pad_h - pad_top\n\n pad_w = w - erase_width\n pad_left = tf.random.uniform(shape=[], minval=0, maxval=pad_w, dtype=tf.int32)\n pad_right = pad_w - pad_left\n\n erase_mask = tf.pad([erase_area], [[0,0],[pad_top, pad_bottom], [pad_left, pad_right], [0,0]], constant_values=1)\n erase_mask = tf.squeeze(erase_mask, axis=0)\n erased_img = tf.multiply(tf.cast(img,tf.float32), tf.cast(erase_mask, tf.float32))\n return tf.cast(erased_img, img.dtype)\n# data augmentation @cdeotte kernel: https://www.kaggle.com/cdeotte/rotation-augmentation-gpu-tpu-0-96\ndef transform_rotation(image, height, rotation):\n # input image - is one image of size [dim,dim,3] not a batch of [b,dim,dim,3]\n # output - image randomly rotated\n DIM = height\n XDIM = DIM%2 #fix for size 331\n \n rotation = rotation * tf.random.uniform([1],dtype='float32')\n # CONVERT DEGREES TO RADIANS\n rotation = math.pi * rotation / 180.\n \n # ROTATION MATRIX\n c1 = tf.math.cos(rotation)\n s1 = tf.math.sin(rotation)\n one = tf.constant([1],dtype='float32')\n zero = tf.constant([0],dtype='float32')\n rotation_matrix = tf.reshape(tf.concat([c1,s1,zero, -s1,c1,zero, zero,zero,one],axis=0),[3,3])\n\n # LIST DESTINATION PIXEL INDICES\n x = tf.repeat( tf.range(DIM//2,-DIM//2,-1), DIM )\n y = tf.tile( tf.range(-DIM//2,DIM//2),[DIM] )\n z = tf.ones([DIM*DIM],dtype='int32')\n idx = tf.stack( [x,y,z] )\n \n # ROTATE DESTINATION PIXELS ONTO ORIGIN PIXELS\n idx2 = K.dot(rotation_matrix,tf.cast(idx,dtype='float32'))\n idx2 = K.cast(idx2,dtype='int32')\n idx2 = K.clip(idx2,-DIM//2+XDIM+1,DIM//2)\n \n # FIND ORIGIN PIXEL VALUES \n idx3 = tf.stack( [DIM//2-idx2[0,], DIM//2-1+idx2[1,]] )\n d = tf.gather_nd(image, tf.transpose(idx3))\n \n return tf.reshape(d,[DIM,DIM,3])\n\ndef transform_shear(image, height, shear):\n # input image - is one image of size [dim,dim,3] not a batch of [b,dim,dim,3]\n # output - image randomly sheared\n DIM = height\n XDIM = DIM%2 #fix for size 331\n \n shear = shear * tf.random.uniform([1],dtype='float32')\n shear = math.pi * shear / 180.\n \n # SHEAR MATRIX\n one = tf.constant([1],dtype='float32')\n zero = tf.constant([0],dtype='float32')\n c2 = tf.math.cos(shear)\n s2 = tf.math.sin(shear)\n shear_matrix = tf.reshape(tf.concat([one,s2,zero, zero,c2,zero, zero,zero,one],axis=0),[3,3]) \n\n # LIST DESTINATION PIXEL INDICES\n x = tf.repeat( tf.range(DIM//2,-DIM//2,-1), DIM )\n y = tf.tile( tf.range(-DIM//2,DIM//2),[DIM] )\n z = tf.ones([DIM*DIM],dtype='int32')\n idx = tf.stack( [x,y,z] )\n \n # ROTATE DESTINATION PIXELS ONTO ORIGIN PIXELS\n idx2 = K.dot(shear_matrix,tf.cast(idx,dtype='float32'))\n idx2 = K.cast(idx2,dtype='int32')\n idx2 = K.clip(idx2,-DIM//2+XDIM+1,DIM//2)\n \n # FIND ORIGIN PIXEL VALUES \n idx3 = tf.stack( [DIM//2-idx2[0,], DIM//2-1+idx2[1,]] )\n d = tf.gather_nd(image, tf.transpose(idx3))\n \n return tf.reshape(d,[DIM,DIM,3])\ndef random_blockout(img, max_holes=8, min_holes=4,\n p=0.75, img_size=512):\n prob=random.random()\n if prob=0.8:\n image = random_blockout(image)\n \n # Flips\n if p_spatial >= .2:\n image = tf.image.stateless_random_flip_left_right(image, seed)\n image = tf.image.stateless_random_flip_up_down(image, seed)\n \n # Rotates\n if p_rotate > .75:\n image = tf.image.rot90(image, k=3) # rotate 270º\n elif p_rotate > .5:\n image = tf.image.rot90(image, k=2) # rotate 180º\n elif p_rotate > .25:\n image = tf.image.rot90(image, k=1) # rotate 90º\n \n if p_rotation >= .3: # Rotation\n image = transform_rotation(image, height=HEIGHT, rotation=45.)\n if p_shift >= .3: # Shift\n image = transform_shift(image, height=HEIGHT, h_shift=15., w_shift=15.)\n if p_shear >= .3: # Shear\n image = transform_shear(image, height=HEIGHT, shear=20.)\n \n # Crops\n if p_crop > .3:\n crop_size = tf.random.uniform([], int(HEIGHT*.7), HEIGHT, dtype=tf.int32)\n image = tf.image.random_crop(image, size=[crop_size, crop_size, CHANNELS])\n elif p_crop > .7:\n if p_crop > .9:\n image = tf.image.central_crop(image, central_fraction=.7)\n elif p_crop > .8:\n image = tf.image.central_crop(image, central_fraction=.8)\n else:\n image = tf.image.central_crop(image, central_fraction=.9)\n \n image = tf.image.resize(image, size=[HEIGHT, WIDTH])\n \n # Pixel-level transforms\n if p_pixel >= .2:\n if p_pixel >= .7:\n image = tf.image.stateless_random_saturation(image, lower=0.2, upper=0.8, seed=seed)\n elif p_pixel >= .5:\n image = tf.image.stateless_random_contrast(image, lower=.3, upper=0.7, seed=seed)\n elif p_pixel >= .3:\n image = tf.image.stateless_random_brightness(image, max_delta=.7, seed=seed)\n else:\n image = tf.image.adjust_gamma(image, gamma=.6)\n\n return image, label\n\n\ndef decode_image(image_data):\n image = tf.image.decode_jpeg(image_data, channels=3)\n image = tf.cast(image, tf.float32) / 255.0 # convert image to floats in [0, 1] range\n image = tf.reshape(image, [*IMAGE_SIZE, 3]) # explicit size needed for TPU\n return image\n\ndef read_labeled_tfrecord(example):\n LABELED_TFREC_FORMAT = {\n \"image\": tf.io.FixedLenFeature([], tf.string), # tf.string means bytestring\n \"class\": tf.io.FixedLenFeature([], tf.int64), # shape [] means single element\n }\n example = tf.io.parse_single_example(example, LABELED_TFREC_FORMAT)\n image = decode_image(example['image'])\n label = tf.cast(example['class'], tf.int32)\n return image, label # returns a dataset of (image, label) pairs\n\ndef read_unlabeled_tfrecord(example):\n UNLABELED_TFREC_FORMAT = {\n \"image\": tf.io.FixedLenFeature([], tf.string), # tf.string means bytestring\n \"id\": tf.io.FixedLenFeature([], tf.string), # shape [] means single element\n # class is missing, this competitions's challenge is to predict flower classes for the test dataset\n }\n example = tf.io.parse_single_example(example, UNLABELED_TFREC_FORMAT)\n image = decode_image(example['image'])\n idnum = example['id']\n return image, idnum # returns a dataset of image(s)\n\ndef load_dataset(filenames, labeled=True, ordered=False):\n # Read from TFRecords. For optimal performance, reading from multiple files at once and\n # disregarding data order. Order does not matter since we will be shuffling the data anyway.\n\n ignore_order = tf.data.Options()\n if not ordered:\n ignore_order.experimental_deterministic = False # disable order, increase speed\n\n dataset = tf.data.TFRecordDataset(filenames, num_parallel_reads=AUTO) # automatically interleaves reads from multiple files\n dataset = dataset.with_options(ignore_order) # uses data as soon as it streams in, rather than in its original order\n dataset = dataset.map(read_labeled_tfrecord if labeled else read_unlabeled_tfrecord, num_parallel_calls=AUTO)\n # returns a dataset of (image, label) pairs if labeled=True or (image, id) pairs if labeled=False\n return dataset\n\n\ndef get_training_dataset():\n dataset = load_dataset(TRAINING_FILENAMES, labeled=True)\n dataset = dataset.map(data_augment, num_parallel_calls=AUTO)\n dataset = dataset.repeat() # the training dataset must repeat for several epochs\n dataset = dataset.shuffle(2048)\n dataset = dataset.batch(BATCH_SIZE)\n dataset = dataset.prefetch(AUTO) # prefetch next batch while training (autotune prefetch buffer size)\n return dataset\n\ndef get_validation_dataset(ordered=False):\n dataset = load_dataset(VALIDATION_FILENAMES, labeled=True, ordered=ordered)\n dataset = dataset.batch(BATCH_SIZE)\n dataset = dataset.cache()\n dataset = dataset.prefetch(AUTO) # prefetch next batch while training (autotune prefetch buffer size)\n return dataset\n\ndef get_test_dataset(ordered=False):\n dataset = load_dataset(TEST_FILENAMES, labeled=False, ordered=ordered)\n dataset = dataset.batch(BATCH_SIZE)\n dataset = dataset.prefetch(AUTO) # prefetch next batch while training (autotune prefetch buffer size)\n return dataset\n\ndef count_data_items(filenames):\n # the number of data items is written in the name of the .tfrec files, i.e. flowers00-230.tfrec = 230 data items\n n = [int(re.compile(r\"-([0-9]*)\\.\").search(filename).group(1)) for filename in filenames]\n return np.sum(n)\n\nNUM_TRAINING_IMAGES = count_data_items(TRAINING_FILENAMES)\nNUM_VALIDATION_IMAGES = count_data_items(VALIDATION_FILENAMES)\nNUM_TEST_IMAGES = count_data_items(TEST_FILENAMES)\nSTEPS_PER_EPOCH = NUM_TRAINING_IMAGES // BATCH_SIZE\nprint('Dataset: {} training images, {} validation images, {} unlabeled test images'.format(NUM_TRAINING_IMAGES, NUM_VALIDATION_IMAGES, NUM_TEST_IMAGES))\nVALIDATION_STEPS = -(-NUM_VALIDATION_IMAGES // BATCH_SIZE)","metadata":{"execution":{"iopub.status.busy":"2021-08-12T14:05:07.888856Z","iopub.execute_input":"2021-08-12T14:05:07.889239Z","iopub.status.idle":"2021-08-12T14:05:07.961167Z","shell.execute_reply.started":"2021-08-12T14:05:07.889206Z","shell.execute_reply":"2021-08-12T14:05:07.960055Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"CHANNELS = 3\ndef display_one_flower(image, title, subplot, red=False, titlesize=16):\n plt.subplot(*subplot)\n plt.axis('off')\n plt.imshow(image)\n if len(title) > 0:\n plt.title(title, fontsize=int(titlesize) if not red else int(titlesize/1.2), color='red' if red else 'black', fontdict={'verticalalignment':'center'}, pad=int(titlesize/1.5))\n return (subplot[0], subplot[1], subplot[2]+1)\n \ndef batch_to_numpy_images_and_labels(data):\n images, labels = data\n numpy_images = images.numpy()\n numpy_labels = labels.numpy()\n if numpy_labels.dtype == object: # binary string in this case, these are image ID strings\n numpy_labels = [None for _ in enumerate(numpy_images)]\n # If no labels, only image IDs, return None for labels (this is the case for test data)\n return numpy_images, numpy_labels\n\ndef display_batch_of_images(databatch, predictions=None):\n \"\"\"This will work with:\n display_batch_of_images(images)\n display_batch_of_images(images, predictions)\n display_batch_of_images((images, labels))\n display_batch_of_images((images, labels), predictions)\n \"\"\"\n # data\n images, labels = batch_to_numpy_images_and_labels(databatch)\n if labels is None:\n labels = [None for _ in enumerate(images)]\n \n # auto-squaring: this will drop data that does not fit into square or square-ish rectangle\n rows = int(math.sqrt(len(images)))\n cols = len(images)//rows\n \n # size and spacing\n FIGSIZE = 13.0\n SPACING = 0.1\n subplot=(rows,cols,1)\n if rows < cols:\n plt.figure(figsize=(FIGSIZE,FIGSIZE/cols*rows))\n else:\n plt.figure(figsize=(FIGSIZE/rows*cols,FIGSIZE))\n \n # display\n for i, (image, label) in enumerate(zip(images[:rows*cols], labels[:rows*cols])):\n title = '' if label is None else CLASSES[label]\n correct = True\n if predictions is not None:\n title, correct = title_from_label_and_target(predictions[i], label)\n dynamic_titlesize = FIGSIZE*SPACING/max(rows,cols)*40+3 # magic formula tested to work from 1x1 to 10x10 images\n subplot = display_one_flower(image, title, subplot, not correct, titlesize=dynamic_titlesize)\n \n #layout\n plt.tight_layout()\n if label is None and predictions is None:\n plt.subplots_adjust(wspace=0, hspace=0)\n else:\n plt.subplots_adjust(wspace=SPACING, hspace=SPACING)\n plt.show()\n\ntraining_dataset = get_training_dataset()\ntraining_dataset = training_dataset.unbatch().batch(20)\ntrain_batch = iter(training_dataset)\ndisplay_batch_of_images(next(train_batch))","metadata":{"execution":{"iopub.status.busy":"2021-08-12T14:05:18.737647Z","iopub.execute_input":"2021-08-12T14:05:18.738036Z","iopub.status.idle":"2021-08-12T14:05:34.559279Z","shell.execute_reply.started":"2021-08-12T14:05:18.738000Z","shell.execute_reply":"2021-08-12T14:05:34.558468Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!pip install -q efficientnet\nimport efficientnet.tfkeras as efn","metadata":{"execution":{"iopub.status.busy":"2021-08-12T14:05:43.525594Z","iopub.execute_input":"2021-08-12T14:05:43.526267Z","iopub.status.idle":"2021-08-12T14:05:52.915253Z","shell.execute_reply.started":"2021-08-12T14:05:43.526218Z","shell.execute_reply":"2021-08-12T14:05:52.914355Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Model\n","metadata":{}},{"cell_type":"code","source":"with strategy.scope():\n pretrained_model = efn.EfficientNetB7(\n weights='noisy-student',\n include_top=False ,\n input_shape=[*IMAGE_SIZE, 3]\n )\n pretrained_model.trainable = True\n \n model1 = tf.keras.Sequential([\n # To a base pretrained on ImageNet to extract features from images...\n pretrained_model,\n tf.keras.layers.GlobalAveragePooling2D(),\n #tf.keras.layers.BatchNormalization(),\n tf.keras.layers.Dense(len(CLASSES), activation='softmax')\n ])\n\nmodel1.compile(\n optimizer=tf.keras.optimizers.Adam(lr=0.0001),\n loss = 'sparse_categorical_crossentropy',\n metrics=['sparse_categorical_accuracy'],\n)\n\nmodel1.summary()\n","metadata":{"execution":{"iopub.status.busy":"2021-08-12T14:05:56.695444Z","iopub.execute_input":"2021-08-12T14:05:56.696074Z","iopub.status.idle":"2021-08-12T14:06:40.591801Z","shell.execute_reply.started":"2021-08-12T14:05:56.696019Z","shell.execute_reply":"2021-08-12T14:06:40.590500Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"with strategy.scope():\n pretrained_model_2 = tf.keras.applications.DenseNet201(\n weights='imagenet',\n include_top=False ,\n input_shape=[*IMAGE_SIZE, 3]\n )\n pretrained_model_2.trainable = True\n \n model2 = tf.keras.Sequential([\n # To a base pretrained on ImageNet to extract features from images...\n pretrained_model_2,\n tf.keras.layers.GlobalAveragePooling2D(),\n tf.keras.layers.BatchNormalization(),\n tf.keras.layers.Dense(len(CLASSES), activation='softmax')\n ])\nmodel2.compile(\n optimizer=tf.keras.optimizers.Adam(lr=0.0001),\n loss = 'sparse_categorical_crossentropy',\n metrics=['sparse_categorical_accuracy'],\n)\n\nmodel2.summary()","metadata":{"execution":{"iopub.status.busy":"2021-08-12T14:07:15.409668Z","iopub.execute_input":"2021-08-12T14:07:15.410077Z","iopub.status.idle":"2021-08-12T14:07:52.881581Z","shell.execute_reply.started":"2021-08-12T14:07:15.410041Z","shell.execute_reply":"2021-08-12T14:07:52.880516Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from matplotlib import pyplot\nearly_stopping = tf.keras.callbacks.EarlyStopping(monitor='val_loss', patience=4, restore_best_weights=True)\n\ndef summarize_diagnostics(history):\n # plot loss\n pyplot.subplot(211)\n pyplot.title('Cross Entropy Loss')\n pyplot.plot(history.history['loss'], color='blue', label='train')\n pyplot.plot(history.history['val_loss'], color='orange', label='test')\n # plot accuracy\n pyplot.subplot(212)\n pyplot.title('Classification Accuracy')\n pyplot.plot(history.history['sparse_categorical_accuracy'], color='blue', label='train')\n pyplot.plot(history.history['val_sparse_categorical_accuracy'], color='orange', label='test')\n # save plot to file\n #filename = sys.argv[0].split('/')[-1]\n pyplot.savefig('result.png')\n pyplot.show()\n \n\nhistory1 = model1.fit(get_training_dataset(),\n validation_data=get_validation_dataset(), \n epochs= 30, \n steps_per_epoch=STEPS_PER_EPOCH)\nsummarize_diagnostics(history1)\n\nhistory2 = model2.fit(get_training_dataset(),\n validation_data=get_validation_dataset(), \n epochs= 30, \n steps_per_epoch=STEPS_PER_EPOCH)\nsummarize_diagnostics(history2)","metadata":{"execution":{"iopub.status.busy":"2021-08-12T14:08:17.003536Z","iopub.execute_input":"2021-08-12T14:08:17.003906Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_ds = get_test_dataset(ordered=True)\n\nprint('Computing predictions...')\ntest_images_ds = test_ds.map(lambda image, idnum: image)\nprobabilities_1 = model1.predict(test_images_ds)\nprobabilities_2 = model2.predict(test_images_ds)\nprobabilities = (probabilities_1 + probabilities_2)/2\npredictions = np.argmax(probabilities, axis=-1)\nprint(predictions)\n\nprint('Generating submission.csv file...')\n\n# Get image ids from test set and convert to unicode\ntest_ids_ds = test_ds.map(lambda image, idnum: idnum).unbatch()\ntest_ids = next(iter(test_ids_ds.batch(NUM_TEST_IMAGES))).numpy().astype('U')\n\n# Write the submission file\nnp.savetxt(\n 'submission.csv',\n np.rec.fromarrays([test_ids, predictions]),\n fmt=['%s', '%d'],\n delimiter=',',\n header='id,label',\n comments='',\n)\n\n# Look at the first few predictions\n!head submission.csv","metadata":{"execution":{"iopub.status.busy":"2021-08-09T07:05:36.276499Z","iopub.execute_input":"2021-08-09T07:05:36.277123Z","iopub.status.idle":"2021-08-09T07:06:23.328063Z","shell.execute_reply.started":"2021-08-09T07:05:36.277069Z","shell.execute_reply":"2021-08-09T07:06:23.32673Z"},"trusted":true},"execution_count":null,"outputs":[]}]}