香港科技大学TensorFlo三天速成课件2.pptx

TensorFlow @UST;;TensorFlow Mechanics ;Machine Learning Basics;Linear Regression;train = tf.train.GradientDescentOptimizer(learning_rate=0.01).minimize(cost);train = tf.train.GradientDescentOptimizer(learning_rate=0.01).minimize(cost);Softmax Classifier;Softmax Classifier;(Deep) Neural Nets;NN tips;Random?;/questions ;NN tips;/posts/2016/06/introduction-deep-learning-python-caffe/;/posts/2016/06/introduction-deep-learning-python-caffe/;NN tips;Overfitting;Am I overfitting?;Solutions for overfitting;Regularization;Regularization;Dropout: A Simple Way to Prevent Neural Networks from Overfitting [Srivastava et al. 2014];TensorFlow implementation;Dropout for MNIST;NN tips;Optimizers;Optimizers;ADAM: a method for stochastic optimization [Kingma et al. 2015];Use Adam Optimizer;TensorFlow @UST;/;;Convolutional Neural Networks for Sentence Classification [Yoon Kim, 2014] ;CNN Basics;CNN;CNN for CT images;Convolution layer and max pooling ;Simple convolution layer Stride: 1x1;Toy image;Simple convolution layer Image: 1,3,3,1 image, Filter: 2,2,1,1, Stride: 1x1, Padding: VALID;Image: 1,3,3,1 image, Filter: 2,2,1,1, Stride: 1x1, Padding: VALID ;1;Image: 1,3,3,1 image, Filter: 2,2,1,1, Stride: 1x1, Padding: SAME;Max Pooling;/hunkim/DeepLearningZeroToAll/blob/master/lab-11-0-cnn_basics.ipynb ;/hunkim/DeepLearningZeroToAll/blob/master/lab-11-0-cnn_basics.ipynb ;/hunkim/DeepLearningZeroToAll/blob/master/lab-11-0-cnn_basics.ipynb ;CNN MNIST 99%;CNN;Simple CNN;; Tensor(Conv2D:0, shape=(?, 28, 28, 32), dtype=float32) Tensor(Relu:0, shape=(?, 28, 28, 32), dtype=float32) Tensor(MaxPool:0, shape=(?, 14, 14, 32), dtype=float32) # L2 ImgIn shape=(?, 14, 14, 32) W2 = tf.Variable(tf.random_normal([3, 3, 32, 64], stddev=0.01)) # Conv -(?, 14, 14, 64) # Pool -(?, 7, 7, 64) L2 = tf.nn.conv2d(L1, W2, strides=[1, 1, 1, 1], padding=SAME) L2 = tf.nn.relu(L2) L2 = tf.nn.max_pool(L2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding=SAME) L2 = tf.reshape(L2, [-1, 7 * 7