笔下虽有千言，胸中实无一策
随笔分类 - 深度学习算法
摘要：Machine/Deep Learning Interview Questions Algorithms/Theory Q1- What’s the trade-off between bias and variance? More reading: Bias-Variance Tradeoff (
阅读全文
摘要：Commonly used functions tf.saved_model.loader.load(sess, tags, export_dir) tf.get_default_graph() # Return the default Graph being used in the current
阅读全文
摘要：Step 1: GPU Instance and AMI The first thing we'll do is select the AMI and an instance with a GPU: Top Left: Service -> EC2 Left Side Bar: Spot Reque
阅读全文
摘要：A Dog Breed Classifier Setting Jupyter Notebook Keras Model ResNet50 Implementation normalization the mean pixel must be subtracted from every pixel i
阅读全文
摘要：Post Hyperparameter optimization for Neural Networks Paper Algorithms for Hyper-Parameter Optimization Note Introduction Sometimes it can be difficult
阅读全文
摘要：Hyperparameter Optimization In the context of machine learning, hyperparameter optimization or model selection is the problem of choosing a set of hyp
阅读全文
摘要：How to check the current version of TensorFlow? This depends on how you installed TensorFlow. Pip installation Run: Note that python is symlinked to /
阅读全文
摘要：A TFRecords file represents a sequence of (binary) strings. The format is not random access, so it is suitable for streaming large amounts of data but
阅读全文
摘要：Overview In Machine learning and statistics, a common task is to fit a model to a set of training data. This model can be used later to make predictio
阅读全文
摘要：概要 Long Short Term Memory networks，简称作LSTM。 Recurrent Neural Networks Recurrent Neural Networks，简称作RNN，其结构包含回环，可以用来解决有信息停留的问题。 其基本机构如下图所示： 如上图所示，神经网络的
阅读全文
摘要：Paper A Torch Library for Action Recognition and Detection Using CNNs and LSTMs [Github] Long-term Recurrent Convolutional Networks for Visual Recogni
阅读全文
摘要：1. Overview Organization Machine Learning > Deep Learning > Deep Reinforcement Learning [Learning Road Map] Reinforcement Learning Architecture Post:
阅读全文
摘要：1. 知乎上关于DRL入门的系列文章 1.1 DQN 从入门到放弃 DQN 从入门到放弃1 DQN与增强学习 DQN 从入门到放弃2 增强学习与MDP DQN 从入门到放弃3 价值函数与Bellman方程 DQN 从入门到放弃4 动态规划与Q-Learning DQN从入门到放弃5 深度解读DQN算
阅读全文
摘要：The state of the art of non-linearity is to use ReLU instead of sigmoid function in deep neural network, what are the advantages? I know that training
阅读全文
摘要：TensorFlow TensorFlow Tutorial Learn Tensorflow TensorFlow based Libraries Keras Among all the Python deep learning libraries, Keras is favorite. We l
阅读全文
浙公网安备 33010602011771号