class EnvSetup: SITE = os.getenv('SITE', 'https://unsplash.com') API = os.getenv('API', 'https://unsplash.com/napi') TOKEN = os.getenv( 'TOKEN', '42ef72d98b48573570f34df9496bdfc643607580f0246152413601e1bd2d5a04') PAGE_LOAD_TIMEOUT_SECONDS = 60 SELENIUM_TIMEOUT_SECONDS = 60 HEADLESS = DataHelper.str_to_bool(os.getenv('HEADLESS', 'False')) NO_SANDBOX = DataHelper.str_to_bool(os.getenv('NO_SANDBOX', 'True')) BROWSER_NAME = os.getenv('BROWSER', 'Chrome') PLATFORM = os.getenv('PLATFORM', 'WINDOWS') SAUCE_LABS = DataHelper.str_to_bool(os.getenv('SAUCE_LABS', 'True')) BUILD_TAG = os.getenv('BUILD_TAG', 'Default Sauce Labs Build') SAUCE_LABS_RDC_USER = '******' SAUCE_LABS_RDC_KEY = '26fcdbb3-0a93-4f51-bc44-8f00e81f46bf'
imdb = tf.keras.datasets.imdb vocab_size = 10000 embed_size = 32 seq_len = 256 batch_size = 512 nb_epoch = 500 (train_x, train_y), (test_x, test_y) = imdb.load_data(num_words=vocab_size) train_x = tf.keras.preprocessing.sequence.pad_sequences(train_x, maxlen=seq_len) test_x = tf.keras.preprocessing.sequence.pad_sequences(test_x, maxlen=seq_len) data_helper = DataHelper(train_x, train_y) # Input X = tf.placeholder(dtype=tf.int32, shape=[None, seq_len]) Y = tf.placeholder(dtype=tf.int32, shape=[None, 1]) global_step = tf.Variable(0, trainable=False) # Model embedding = tf.Variable(tf.truncated_normal([vocab_size, embed_size])) inputs = tf.nn.embedding_lookup(embedding, X) # [batch_size * 256 * 100] # Pooling pooling = tf.layers.max_pooling1d(inputs, 2, strides=1, padding="valid") # [?,32] global_pooling = tf.reduce_mean(pooling, 1)
# distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # ============================================================================== import tensorflow as tf from tensorflow import keras from helper.data_helper import DataHelper (x_train, y_train), (x_test, y_test) = keras.datasets.mnist.load_data() x_train, x_test = x_train / 255.0, x_test / 255.0 y_train, y_test = keras.utils.to_categorical( y_train), keras.utils.to_categorical(y_test) data_helper = DataHelper(x_train, y_train) n_input = 28 # MNIST data input (img shape: 28*28) n_steps = 28 # timesteps n_hidden = 128 # hidden layer num of features n_classes = 10 # MNIST total classes (0-9 digits) learning_rate = 0.001 training_iters = 100000 batch_size = 100 display_step = 10 x = tf.placeholder(tf.float32, [None, n_steps, n_input]) y = tf.placeholder(tf.float32, [None, n_classes]) weights = tf.Variable(tf.truncated_normal([n_hidden, n_classes], stddev=0.1))
# ============================================================================== import numpy as np import tensorflow as tf from tensorflow import keras from helper.data_helper import DataHelper (train_data, train_labels), (test_data, test_labels) = keras.datasets.boston_housing.load_data() mean = train_data.mean(axis=0) std = train_data.std(axis=0) train_data = (train_data - mean) / std test_data = (test_data - mean) / std data_helper = DataHelper(train_data, train_labels) feature_num = train_data.shape[1] x = tf.placeholder(dtype=tf.float32, shape=[None, feature_num], name='feature') y = tf.placeholder(dtype=tf.float32, shape=[None, 1], name='target') global_step = tf.Variable(0, trainable=False, name='global_step') l1 = tf.layers.dense(x, 64, activation=tf.nn.relu) l2 = tf.layers.dense(l1, 64, activation=tf.nn.relu) pred = tf.layers.dense(l2, 1) mae, mae_op = tf.metrics.mean_absolute_error(labels=y, predictions=pred) loss = tf.losses.mean_squared_error(labels=y, predictions=pred) optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.001)
import numpy as np import tensorflow as tf from helper.data_helper import DataHelper mnist = tf.keras.datasets.mnist (x_train, y_train), (x_test, y_test) = mnist.load_data() x_train, x_test = x_train / 255.0, x_test / 255.0 m_train = x_train.shape[0] m_test = x_test.shape[0] x_train = np.reshape(x_train, [m_train, -1]) x_test = np.reshape(x_test, [m_test, -1]) data_helper = DataHelper(data=x_train, label=y_train) X = tf.placeholder(tf.float32, [None, 784], name="X") Y_truth = tf.placeholder(tf.float32, [None, 10], name="Y") PKeep = tf.placeholder(tf.float32) W1 = tf.Variable(tf.truncated_normal([784, 512], stddev=0.1), name='W1') B1 = tf.Variable(tf.ones([512]) / 10, name='B1') W2 = tf.Variable(tf.truncated_normal([512, 128], stddev=0.1), name='W2') B2 = tf.Variable(tf.ones([128]) / 10, name='B2') W3 = tf.Variable(tf.truncated_normal([128, 10], stddev=0.1), name='W3') B3 = tf.Variable(tf.ones([10]) / 10, name='B3') Y1 = tf.nn.relu(tf.matmul(X, W1) + B1) Y1 = tf.nn.dropout(Y1, PKeep) Y2 = tf.nn.relu(tf.matmul(Y1, W2) + B2)
import tensorflow as tf from tensorflow import keras from helper.data_helper import DataHelper (x_train, y_train), (x_test, y_test) = keras.datasets.cifar10.load_data() x_train, x_test = x_train / 255, x_test / 255 # x_train = x_train[:20] # x_test = x_test[:20] # y_train = y_train[:20] # y_test = y_test[:20] y_train = keras.utils.to_categorical(y_train) y_test = keras.utils.to_categorical(y_test) data_helper = DataHelper(x_train, y_train) X = tf.placeholder(tf.float32, shape=[None, 32, 32, 3], name='image') Y = tf.placeholder(tf.float32, shape=[None, 10], name='label') pKeep = tf.placeholder(tf.float32) K = 6 L = 12 M = 18 # convolution network W1 = tf.Variable(tf.truncated_normal([5, 5, 3, K], stddev=0.1)) B1 = tf.Variable(tf.ones([K]) / 10) W2 = tf.Variable(tf.truncated_normal([4, 4, K, L], stddev=0.1)) B2 = tf.Variable(tf.ones([L]) / 10) W3 = tf.Variable(tf.truncated_normal([3, 3, L, M], stddev=0.1))