def main(_): tfe.enable_eager_execution() # Ground-truth constants. true_w = [[-2.0], [4.0], [1.0]] true_b = [0.5] noise_level = 0.01 # Training constants. batch_size = 64 learning_rate = 0.1 print("True w: %s" % true_w) print("True b: %s\n" % true_b) model = LinearModel() dataset = synthetic_dataset(true_w, true_b, noise_level, batch_size, 20) device = "gpu:0" if tfe.num_gpus() else "cpu:0" print("Using device: %s" % device) with tf.device(device): optimizer = tf.train.GradientDescentOptimizer(learning_rate) fit(model, dataset, optimizer, verbose=True, logdir=FLAGS.logdir) print("\nAfter training: w = %s" % model.variables[0].numpy()) print("\nAfter training: b = %s" % model.variables[1].numpy())
def main(_): tfe.enable_eager_execution() (device, data_format) = ('/gpu:0', 'channels_first') if FLAGS.no_gpu or tfe.num_gpus() <= 0: (device, data_format) = ('/cpu:0', 'channels_last') print('Using device %s, and data format %s.' % (device, data_format)) # Load the datasets train_ds = dataset.train(FLAGS.data_dir).shuffle(60000).batch( FLAGS.batch_size) test_ds = dataset.test(FLAGS.data_dir).batch(FLAGS.batch_size) # Create the model and optimizer model = mnist.Model(data_format) optimizer = tf.train.MomentumOptimizer(FLAGS.lr, FLAGS.momentum) if FLAGS.output_dir: # Create directories to which summaries will be written # tensorboard --logdir=<output_dir> # can then be used to see the recorded summaries. train_dir = os.path.join(FLAGS.output_dir, 'train') test_dir = os.path.join(FLAGS.output_dir, 'eval') tf.gfile.MakeDirs(FLAGS.output_dir) else: train_dir = None test_dir = None summary_writer = tf.contrib.summary.create_file_writer( train_dir, flush_millis=10000) test_summary_writer = tf.contrib.summary.create_file_writer( test_dir, flush_millis=10000, name='test') checkpoint_prefix = os.path.join(FLAGS.checkpoint_dir, 'ckpt') step_counter = tf.train.get_or_create_global_step() checkpoint = tfe.Checkpoint( model=model, optimizer=optimizer, step_counter=step_counter) # Restore variables on creation if a checkpoint exists. checkpoint.restore(tf.train.latest_checkpoint(FLAGS.checkpoint_dir)) # Train and evaluate for 10 epochs. with tf.device(device): for _ in range(10): start = time.time() with summary_writer.as_default(): train(model, optimizer, train_ds, step_counter, FLAGS.log_interval) end = time.time() print('\nTrain time for epoch #%d (%d total steps): %f' % (checkpoint.save_counter.numpy() + 1, step_counter.numpy(), end - start)) with test_summary_writer.as_default(): test(model, test_ds) checkpoint.save(checkpoint_prefix)
def main(_): tfe.enable_eager_execution() (device, data_format) = ('/gpu:0', 'channels_first') if FLAGS.no_gpu or tfe.num_gpus() <= 0: (device, data_format) = ('/cpu:0', 'channels_last') print('Using device %s, and data format %s.' % (device, data_format)) # Load the datasets (train_ds, test_ds) = load_data(FLAGS.data_dir) train_ds = train_ds.shuffle(60000).batch(FLAGS.batch_size) # Create the model and optimizer model = MNISTModel(data_format) optimizer = tf.train.MomentumOptimizer(FLAGS.lr, FLAGS.momentum) if FLAGS.output_dir: train_dir = os.path.join(FLAGS.output_dir, 'train') test_dir = os.path.join(FLAGS.output_dir, 'eval') tf.gfile.MakeDirs(FLAGS.output_dir) else: train_dir = None test_dir = None summary_writer = tf.contrib.summary.create_file_writer( train_dir, flush_millis=10000) test_summary_writer = tf.contrib.summary.create_file_writer( test_dir, flush_millis=10000, name='test') checkpoint_prefix = os.path.join(FLAGS.checkpoint_dir, 'ckpt') with tf.device(device): for epoch in range(1, 11): with tfe.restore_variables_on_create( tf.train.latest_checkpoint(FLAGS.checkpoint_dir)): global_step = tf.train.get_or_create_global_step() start = time.time() with summary_writer.as_default(): train_one_epoch(model, optimizer, train_ds, FLAGS.log_interval) end = time.time() print('\nTrain time for epoch #%d (global step %d): %f' % ( epoch, global_step.numpy(), end - start)) with test_summary_writer.as_default(): test(model, test_ds) all_variables = ( model.variables + optimizer.variables() + [global_step]) tfe.Saver(all_variables).save( checkpoint_prefix, global_step=global_step)
cs20.stanford.edu Chip Huyen ([email protected]) & Akshay Agrawal ([email protected]) Lecture 04 """ import os os.environ['TF_CPP_MIN_LOG_LEVEL']='2' import numpy as np import tensorflow as tf import tensorflow.contrib.eager as tfe import utils from examples import word2vec_utils tfe.enable_eager_execution() # Model hyperparameters VOCAB_SIZE = 50000 BATCH_SIZE = 128 EMBED_SIZE = 128 # dimension of the word embedding vectors SKIP_WINDOW = 1 # the context window NUM_SAMPLED = 64 # number of negative examples to sample LEARNING_RATE = 1.0 NUM_TRAIN_STEPS = 100000 VISUAL_FLD = 'visualization' SKIP_STEP = 5000 # Parameters for downloading data DOWNLOAD_URL = 'http://mattmahoney.net/dc/text8.zip' EXPECTED_BYTES = 31344016
def main(argv): parser = MNISTEagerArgParser() flags = parser.parse_args(args=argv[1:]) tfe.enable_eager_execution() # Automatically determine device and data_format (device, data_format) = ('/gpu:0', 'channels_first') if flags.no_gpu or tfe.num_gpus() <= 0: (device, data_format) = ('/cpu:0', 'channels_last') # If data_format is defined in FLAGS, overwrite automatically set value. if flags.data_format is not None: data_format = flags.data_format print('Using device %s, and data format %s.' % (device, data_format)) # Load the datasets train_ds = mnist_dataset.train(flags.data_dir).shuffle(60000).batch( flags.batch_size) test_ds = mnist_dataset.test(flags.data_dir).batch(flags.batch_size) # Create the model and optimizer model = mnist.create_model(data_format) optimizer = tf.train.MomentumOptimizer(flags.lr, flags.momentum) # Create file writers for writing TensorBoard summaries. if flags.output_dir: # Create directories to which summaries will be written # tensorboard --logdir=<output_dir> # can then be used to see the recorded summaries. train_dir = os.path.join(flags.output_dir, 'train') test_dir = os.path.join(flags.output_dir, 'eval') tf.gfile.MakeDirs(flags.output_dir) else: train_dir = None test_dir = None summary_writer = tf.contrib.summary.create_file_writer( train_dir, flush_millis=10000) test_summary_writer = tf.contrib.summary.create_file_writer( test_dir, flush_millis=10000, name='test') # Create and restore checkpoint (if one exists on the path) checkpoint_prefix = os.path.join(flags.model_dir, 'ckpt') step_counter = tf.train.get_or_create_global_step() checkpoint = tfe.Checkpoint( model=model, optimizer=optimizer, step_counter=step_counter) # Restore variables on creation if a checkpoint exists. checkpoint.restore(tf.train.latest_checkpoint(flags.model_dir)) # Train and evaluate for a set number of epochs. with tf.device(device): for _ in range(flags.train_epochs): start = time.time() with summary_writer.as_default(): train(model, optimizer, train_ds, step_counter, flags.log_interval) end = time.time() print('\nTrain time for epoch #%d (%d total steps): %f' % (checkpoint.save_counter.numpy() + 1, step_counter.numpy(), end - start)) with test_summary_writer.as_default(): test(model, test_ds) checkpoint.save(checkpoint_prefix)
#!/usr/bin/env python3 # -*- coding: utf-8 -*- """ Created on Wed Nov 21 16:48:51 2018 @author: xsxsz """ import numpy as np import tensorflow as tf import tensorflow.contrib.eager as tfe tfe.enable_eager_execution() a=tf.constant(2) b=tf.constant(3) c=a+b d=a*b print('a=%i'%a) print('-----------') print('b=%i'%b) print('-----------') print('c=%i'%c) print('-----------') print('d=%i'%d) print('-----------')
from __future__ import print_function import tensorflow as tf import tensorflow.contrib.eager as tfe import numpy as np # Set Eager API tfe.enable_eager_execution() # 启动动态图(默认为静态图) # 动态图中 tensor 转 numpy a.numpy() a is tensor # numpy to tensor tf.convert_to_tensor(a) a is numpy # Import MNIST data from tensorflow.examples.tutorials.mnist import input_data mnist = input_data.read_data_sets("MNIST_data/", one_hot=False) def pad_image(image, pad_h=32, pad_w=32): h, w = image.shape[:2] assert h < pad_h assert w < pad_w err_h = pad_h - h top_pad = err_h // 2 bottom_pad = err_h - top_pad err_w = pad_w - w left_pad = err_w // 2 right_pad = err_w - left_pad padding = [(top_pad, bottom_pad), (left_pad, right_pad), (0, 0)] image = np.pad(image, padding, mode='constant', constant_values=0) return image
def main(argv): parser = MNISTEagerArgParser() flags = parser.parse_args(args=argv[1:]) tfe.enable_eager_execution() # Automatically determine device and data_format (device, data_format) = ('/gpu:0', 'channels_first') if flags.no_gpu or tfe.num_gpus() <= 0: (device, data_format) = ('/cpu:0', 'channels_last') # If data_format is defined in FLAGS, overwrite automatically set value. if flags.data_format is not None: data_format = flags.data_format print('Using device %s, and data format %s.' % (device, data_format)) # Load the datasets train_ds = mnist_dataset.train(flags.data_dir).shuffle(60000).batch( flags.batch_size) test_ds = mnist_dataset.test(flags.data_dir).batch(flags.batch_size) # Create the model and optimizer model = mnist.create_model(data_format) optimizer = tf.train.MomentumOptimizer(flags.lr, flags.momentum) # Create file writers for writing TensorBoard summaries. if flags.output_dir: # Create directories to which summaries will be written # tensorboard --logdir=<output_dir> # can then be used to see the recorded summaries. train_dir = os.path.join(flags.output_dir, 'train') test_dir = os.path.join(flags.output_dir, 'eval') tf.gfile.MakeDirs(flags.output_dir) else: train_dir = None test_dir = None summary_writer = tf.contrib.summary.create_file_writer(train_dir, flush_millis=10000) test_summary_writer = tf.contrib.summary.create_file_writer( test_dir, flush_millis=10000, name='test') # Create and restore checkpoint (if one exists on the path) checkpoint_prefix = os.path.join(flags.model_dir, 'ckpt') step_counter = tf.train.get_or_create_global_step() checkpoint = tfe.Checkpoint(model=model, optimizer=optimizer, step_counter=step_counter) # Restore variables on creation if a checkpoint exists. checkpoint.restore(tf.train.latest_checkpoint(flags.model_dir)) # Train and evaluate for a set number of epochs. with tf.device(device): for _ in range(flags.train_epochs): start = time.time() with summary_writer.as_default(): train(model, optimizer, train_ds, step_counter, flags.log_interval) end = time.time() print('\nTrain time for epoch #%d (%d total steps): %f' % (checkpoint.save_counter.numpy() + 1, step_counter.numpy(), end - start)) with test_summary_writer.as_default(): test(model, test_ds) checkpoint.save(checkpoint_prefix)
from __future__ import absolute_import, division, print_function, unicode_literals # from keras import backend as K import tensorflow as tf import keras import numpy as np import tensorflow.contrib.eager as tfe from keras.preprocessing import sequence from sklearn.model_selection import train_test_split import time from keras.initializers import Constant from helpers import loadGloveModel, evaluate_acc, hotflip_attack, get_pred, attack, attack_dataset print(tf.__version__) if __name__ == '__main__': # 1.0 get the data tfe.enable_eager_execution(device_policy=tfe.DEVICE_PLACEMENT_SILENT) imdb = keras.datasets.imdb num_features = 20000 (train_data, train_labels), (test_data, test_labels) = imdb.load_data(num_words=num_features) print("Training entries: {}, labels: {}".format(len(train_data), len(train_labels))) maxlen = 80 x_train = sequence.pad_sequences(train_data, maxlen=maxlen) x_test = sequence.pad_sequences(test_data, maxlen=maxlen) print('x_train shape:', x_train.shape) print('x_test shape:', x_test.shape) # 1.1 get the word indices word_index = imdb.get_word_index() # The first indices are reserved
# In[ ]: # This Python 3 environment comes with many helpful analytics libraries installed # It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python # For example, here's several helpful packages to load in import os import glob from pathlib import Path import numpy as np # linear algebra import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv) import matplotlib.pyplot as plt import seaborn as sns import tensorflow as tf import tensorflow.contrib.eager as tfe tfe.enable_eager_execution() #enable the eager mode before doing any operation from keras.preprocessing import image from skimage.io import imread, imsave, imshow from keras.utils import to_categorical from sklearn.model_selection import train_test_split np.random.seed(111) color = sns.color_palette() get_ipython().run_line_magic('matplotlib', 'inline') # Input data files are available in the "../input/" directory. # For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory from subprocess import check_output print(check_output(["ls", "../input"]).decode("utf8"))
from __future__ import print_function import numpy as np import tensorflow as tf import tensorflow.contrib.eager as tfe import sys import cv2 from svsutils import Slide config = tf.ConfigProto() config.gpu_options.allow_growth = True tfe.enable_eager_execution(config=config) print('\nslide at 5x') slide_path = '/home/nathan/data/ccrcc/TCGA_KIRC/' slide_path += 'TCGA-A3-3346-01Z-00-DX1.95280216-fd71-4a03-b452-6e3d667f2542.svs' preprocess_fn = lambda x: (x * (2 / 255.)) - 1 s = Slide(slide_path=slide_path, process_mag=5, process_size=128, preprocess_fn=preprocess_fn) s.print_info() ds = tf.data.Dataset.from_generator(generator=s.generator, output_types=tf.float32) ds = tfe.Iterator(ds) for idx, x in enumerate(ds): print x.shape, x.dtype # cv2.imwrite('debug/{}.jpg'.format(idx), x.numpy()[:,:,::-1])
can be converted to a graph that can be further optimized and/or extracted for deployment in production without changing code. " - Rajat Monga ''' from __future__ import absolute_import, division, print_function import numpy as np import tensorflow as tf import tensorflow.contrib.eager as tfe # Set Eager API print("Setting Eager mode...") ''' 报错:tf.enable_eager_execution must be called at program startup. 这时候需要重启spyder的kernal即可.应该是清除之前的graph模式. ''' tfe.enable_eager_execution() #启动热模式,这样输入什么就运行什么 # Define constant tensors print("Define constant tensors") a = tf.constant(2) print("a = %i" % a) b = tf.constant(3) print("b = %i" % b) # Run the operation without the need for tf.Session print("Running operations, without tf.Session") c = a + b print("a + b = %i" % c) d = a * b print("a * b = %i" % d)
def func_cuRadiomics(yaml_addr, image, mask): tfe.enable_eager_execution() a = tf.constant(value=1) _RadiomicsGLCMModule = tf.load_op_library('./build/libRadiomics.so').radiomics features_name_glcm = ["Autocorrelation", "JointAverage", "ClusterProminence", "ClusterShade", "ClusterTendency", "Contrast", "Correlation", "DifferenceAverage", "DifferenceEntropy", "DifferenceVariance", "JointEnergy", "JointEntropy", "Imc1", "Imc2", "Idm", "Idmn", "Id", "Idn", "InverseVariance", "MaximumProbability", "SumAverage", "SumEntropy", "SumSquares" ] features_name_firstorder = \ ["Energy", "Entropy", "Minimum", "TenthPercentile", "NintiethPercentile", "Maximum", "Mean", "Median", "InterquartileRange", "Range", "MAD", "rMAD", "RMS", "StandardDeviation", "Skewness", "Kurtosis", "Varianc", "Uniformity"] # Reading Parameters if Feature Extraction f = open(yaml_addr) parameters = yaml.load(f) #Range = parameters['Range'] FirstOrder = parameters['FirstOrder'] GLCM = parameters['GLCM'] label = parameters['label'] # arr_shape = normed_arr_img0.shape Range = [np.min(image).astype('int'), np.max(image).astype('int')] SETTING = np.array([Range[0], Range[1], FirstOrder, GLCM, label]) #arr_shape = image.shape image[np.where(mask != label)] = -1 arr_features = _RadiomicsGLCMModule(image, SETTING) NumOfFeatures = 0 Names = [] if GLCM == 1: Names = Names + features_name_glcm NumOfFeatures += 23 if FirstOrder == 1: Names = Names + features_name_firstorder NumOfFeatures += 18 arr_features = np.reshape(arr_features, newshape=[NumOfFeatures, image.shape[0]]) RadiomicsFeatures = {} for i in range(len(Names)): RadiomicsFeatures[Names[i]] = arr_features[i, :] return RadiomicsFeatures