![](https://img-blog.csdnimg.cn/20201014180756928.png?x-oss-process=image/resize,m_fixed,h_64,w_64)
pythonMachineLearningInAction
文章平均质量分 96
LIQING LIN
这个作者很懒,什么都没留下…
展开
-
d2_struct.unpack_gzip_mkdir_Derivative of Softmax_Crossentropy_tensor_Scalar_Vector_rank_matrix
This chapter coversA first example of a neural network Tensors and tensor operations How neural networks learn via backpropagation and gradient descent Understanding deep learning requires familiarity with many simple mathematical concepts: tensor...原创 2022-11-25 09:11:08 · 2868 阅读 · 0 评论 -
mpf11_Learning rate_Activation_Loss_Optimizer_Quadratic Program_NewtonTaylor_L-BFGS_Nesterov_Hessian
Linear,Sigmoid,Hard Tanh,Leaky ReLU,PRelu,SeLU,Softplus,Softsign,MAE,MSE,Huber, Logistic,Cross entropy,Focal,Hinge,Exponential,Softmax, Quantile,SGD,Momentum,NAG,AdaGrad,RMSprop,AdaMax,Nadam,Adadelta,Timedecay,Piecewise constant,Performance,1cycle,Hessian原创 2022-10-13 04:48:08 · 929 阅读 · 0 评论 -
mpf10_yfinan_Explained variance_R2_ols_cointegration_Gradient Boost_lbfgs_热力图sns ticklabel_SVM_confu
mpf10_yfinan_Explained variance_cointegration_Gradient Boost_lbfgs_sns ticklabel_SVM svc_confusion matrix_heatmap_accuracy score, precision score, recall score, F1 score_MSE, MAE, explained variance score, R2 score_OLS, ridge, LASSO, elastic net, L1 L2正则原创 2022-09-14 19:05:33 · 1807 阅读 · 0 评论 -
t3_Predicting the Markets w ML_sklearn_scatter_PairGrid_R-squared_log returns_Lasso_ridge_KNN_SVM_LR
In the last chapter, we learned how to design trading strategies, create trading signals, and implement advanced concepts, such as seasonality in trading instruments. Understanding those concepts in greater detail is a vast field comprising stochastic...原创 2021-12-03 23:11:00 · 5634 阅读 · 0 评论 -
19_3_Training Keras models with TensorFlow Cloud
19_Training and Deploying TensorFlowModels at Scale_walk目录_TensorFlow Serving_requests_REST_gRPC_Docker_Google API Client Library_gpu :https://blog.csdn.net/Linli522362242/article/details/11932341119_2_Training & Deploying TensorFlowModels_%%writefi.原创 2021-10-29 09:18:28 · 347 阅读 · 0 评论 -
m07_Follow RecommendationsUsing Graph Mining_job_os创建子目录_sort dict by value_NetworkX_Silhou_precompu
Graphs can be used to represent a wide range of phenomena. This is particularly true for online social networks, and the Internet of Things (IoT). Graph mining is big business, with websites such as Facebook running on data analysis experiments perfo...原创 2021-10-22 18:13:08 · 731 阅读 · 0 评论 -
n05_Reinforcement Q-Learnining_MDP_getattr_Monte Carlo_Blackjack_Driving office_ε-greedy_SARSA_Bellm
Reinforcement learning (RL) is the third major section of machine learning after supervised and unsupervised learning. These techniques have gained a lot of traction in recent years in the application of artificial intelligence. In reinforcement learn...原创 2021-10-20 07:01:32 · 1428 阅读 · 0 评论 -
19_2_Training & Deploying TensorFlowModels_%%writefile UsageError_colab_文件名含有空格_No dashboard_gcp
Training Models Across Multiple Devices There are two main approaches to training a single model across multiple devices: model parallelism, where the model is split across the devices, and data parallelism, where the model is replicated across every...原创 2021-10-27 12:21:20 · 1905 阅读 · 0 评论 -
19_训练 & 部署 TFModels at Scale_walk目录_TensorFlow Serving_requests_REST_gRPC_Docker_gcp客户端库_gpu
Once you have a beautiful model that makes amazing predictions, what do you do with it? Well, you need to put it in production! This could be as simple as running the model on a batch of data and perhaps writing a script that runs this model every nig...原创 2021-08-12 05:02:07 · 1843 阅读 · 0 评论 -
A Full Hardware Guide to Deep Learning
https://timdettmers.com/2018/12/16/deep-learning-hardware-guide/#more-121https://blog.csdn.net/jiangjunshow/article/details/97894631Conclusion / TL;DRGPU: RTX 2070 or RTX 2080 Ti. GTX 1070, GTX 1080, GTX 1070 Ti, and GTX 1080 Ti from eBay are good to原创 2021-08-09 22:15:43 · 154 阅读 · 0 评论 -
18_3Reinforcement Learning_LunarLander_SpaceInvader
Exercises1. How would you define Reinforcement Learning? How is it different from regularsupervised or unsupervised learning?2. Can you think of three possible applications of RL that were not mentioned inthis chapter? For each of them, what is the env原创 2021-08-03 23:39:56 · 1393 阅读 · 0 评论 -
18_Reinforcement Learning_CartPole_reduce_mean_Q-Value Iteration_Q-learning_DQN_get_weights_replay
Reinforcement Learning (RL) is one of the most exciting fields of Machine Learning today, and also one of the oldest. It has been around since the 1950s, producing many interesting applications over the years,(For more details, be sure to check out Ri...原创 2021-07-24 09:37:45 · 1723 阅读 · 1 评论 -
18_2Reinforcement Learning_\r_end=““_Deep Q-Learning_Double DQN_Dueling DQN_TF-Agents
Deep Q-Learning Variants原创 2021-07-31 14:21:59 · 1626 阅读 · 0 评论 -
cp18_Reinforcement Learning for Markov Decision Making in Env_Bellman_Q-learning_Q-Value Iteration
In the previous chapters, we focused on supervised and unsupervised machine learning. We also learned how to leverage artificial neural networks and deep learning to tackle problems encountered with these types of machine learning. As you'll recall, s...原创 2021-07-15 06:56:18 · 2568 阅读 · 2 评论 -
17_2Representation Learning and Generative Learning Deep Convolutional_Progressive Growing Style GAN
Generative Adversarial Networks原创 2021-06-05 18:58:32 · 1579 阅读 · 0 评论 -
cp17_2GAN for Synthesizing_upsample_Transposed_Batch normalization_DCGAN_KL_JS divergence_双轴_EM_tape
cp17_GAN for Synthesizing Data_fully connected layer 2 convolutional_colab_ax.transAxes_twiny_spineImproving the quality of synthesized images using a convolutional and Wasserstein GAN原创 2021-06-02 08:30:30 · 1189 阅读 · 0 评论 -
cp17_GAN for Synthesizing Data_fully connected layer 2 convolutional_colab_ax.transAxes_twiny_spine
In the https://blog.csdn.net/Linli522362242/article/details/113846940, we focused on recurrent neural networks for modeling sequences. In this chapter, we will explore generative adversarial networks (GANs) and see their application in synthesizing ne...原创 2021-05-28 18:01:58 · 1078 阅读 · 0 评论 -
17_Representation Tying权重 CNN RNN denoising Sparse Autoencoder_潜在loss_accuracy_TSNE_KL Divergence_L1
Autoencoders are artificial neural networks capable of learning dense representations of the input data, called latent representations or codings, without any supervision (i.e., the training set is unlabeled). These codings typically have a much lower...原创 2021-05-24 06:52:33 · 1014 阅读 · 0 评论 -
16_4可变长度_pad_mask_plain seq-to-seq_有无状态attention_sampled softmax_ragged_rank_pylist_encod_gru_matsho
Exercises1. What are the pros and cons of using a stateful RNN versus a stateless RNN?2. Why do people use Encoder–Decoder RNNs rather than plain sequence-tosequenceRNNs for automatic translation?3. How can you deal with variable-length input sequen...原创 2021-05-09 05:34:27 · 1883 阅读 · 0 评论 -
16_3_NLP RNNs Encoder Decoder 多头 Attention_complexity_max path length_sequential operations_colorbar
Attention MechanismsFigure 16-3. A simple machine translation model Consider the path from the word “milk” to its translation “lait” in Figure 16-3: it is quite long! This means that a representation of this word (along with all the otherwords) ne...原创 2021-04-23 18:09:19 · 2564 阅读 · 1 评论 -
16_2rnn_output_colabTensorboard_curdir_Pretrained Embed_Schedu_TrainingSample_id_Encoder_Beam搜索_mask
16_NLP stateful CharRNN_window_Tokenizer_stationary_celab_ResetState_character-level model toword level model_regex_IMDb:原创 2021-04-14 07:01:18 · 967 阅读 · 0 评论 -
16_NLP stateful CharRNN_window_Tokenizer_stationary_colab_ResetState_character word level_regex_IMDb
When Alan Turing imagined his famous Turing test (Alan Turing, “Computing Machinery and Intelligence,” Mind 49 (1950): 433–460.) in 1950, his objective was to evaluate a machine’s ability to match human intelligence. He could have tested for many thin...原创 2021-04-08 13:34:25 · 1399 阅读 · 1 评论 -
15_2_顺序数据10值Us RNNs_1D CNNs_GRU_wavenet_get_file_glob_readlines_colab_轮廓图quickdraw_chorales合唱_window
15_RNN_naive_linear_CNN预测顺序数据10值_scalar_plt.sca_labelpad_curve_Layer Normal_TimeDistributed_LSTM_GRU原创 2021-04-01 05:56:56 · 772 阅读 · 0 评论 -
15_RNN_naive_linear_CNN预测顺序数据10值_scalar_plt.sca_labelpad_curve_Layer Normal_TimeDistributed_LSTM_GRU
The batter[ˈbætər]击球员 hits the ball. The outfielder[ˈaʊtfi:ldə(r)]外场手 immediately starts running, anticipating the ball’s trajectory[trəˈdʒektəri]轨线. He tracks it, adapts his movements, and finally catches it (under a thunder of applause). Predicting ...原创 2021-03-27 04:12:29 · 1675 阅读 · 1 评论 -
14_4计算机视觉 Fully Conv dense_mnist_compute parameters_run out of RAMemo_local response normal_Semantic
14_Deep Computer Vision Using Convolutional Neural Networks_pool_GridSpec:https://blog.csdn.net/Linli522362242/article/details/10830226614_Deep Computer Vision Using Convolutional Neural Networks_2_LeNet-5_ResNet-50_ran out of datahttps://blog.csdn.net/L原创 2021-03-17 04:57:53 · 1871 阅读 · 1 评论 -
cp16_2_建模顺序数据_RNNs_Bidirectional LSTM_gz_colab_gpu_movie_eager_prefetchDataset_text泛化_Self-Attention
cp16_Model Sequential_Output_Hidden_Recurrent NNs_LSTM_aclImdb_IMDb_Embed_token_py_function_GRU_Gate:Building an RNN model for the sentiment analysis task Since we have very long sequences, we are going to use an LSTM(Long short-term memory) layer ...原创 2021-03-07 08:09:20 · 1485 阅读 · 3 评论 -
cp16_Model Sequential_Output_Hidden_Recurrent NNs_LSTM_aclImdb_IMDb_Embed_token_py_function_GRU_Gate
In the previous chapter cp15_Classifying Images with Deep Convolutional NN_Loss_Cross Entropy_ax.text_mnist_ CelebA_Colab_ckhttps://blog.csdn.net/Linli522362242/article/details/108414534, we focused on convolutional neural networks (CNNs). We covered...原创 2021-02-28 20:25:18 · 1106 阅读 · 1 评论 -
cp14_2_Layers_config_numeric_continuou_Feature Column_boosted tree_n_batches_per_layer_repeat_estima
cp14_TF_v1_v2_TensorSpec_rank_trainable_variables_autodiff_keras_Model_API_set_label_coords_custom原创 2021-02-18 07:05:03 · 1075 阅读 · 2 评论 -
cp14_TF_v1_v2_TensorSpec_rank_trainable_variables_autodiff_keras_Model_API_set_label_coords_custom
In cp13_Parallelizing NN Training w TF_printoptions(precision)_squeeze_shuffle_batch_repeat_image处理_map : https://blog.csdn.net/Linli522362242/article/details/112386820cp13_2_PNN Training_tfrecord files_image process_mnist_gradient_iris_exponent_Adagrad_A.原创 2021-02-10 16:33:32 · 809 阅读 · 1 评论 -
好书分享Power BI_tableau_Web application with Python_Deep Learning_Opencv_Python Game
Power BIBeginning Power BI A Practical Guide to Self-Service Data Analytics with Excel 2016 and Power BI Desktop.pdf:http://projanco.com/Library/Beginning%20Power%20BI%20A%20Practical%20Guide%20to%20Self-Service%20Data%20Analytics%20with%20Excel%202016%.原创 2021-02-06 13:09:45 · 727 阅读 · 2 评论 -
cp13_2_PNN Training_tfrecord files_image process_mnist_gradient_iris_exponent_Adagrad_Adam_tanh_Relu
cp13_Parallelizing NN Training w TF_printoptions(precision)_squeeze_shuffle_batch_repeat_image处理_map_celeba_tfrecord原创 2021-02-05 13:21:57 · 1164 阅读 · 0 评论 -
cp13_Parallelizing NN Training w TF_printoptions(precision)_squeeze_shuffle_batch_repeat_image处理_map
In this chapter, we will move on from the mathematical foundations of machine learning and deep learning to focus on TensorFlow. TensorFlow is one of the most popular deep learning libraries currently available, and it lets us implement neural network...原创 2021-01-28 10:56:30 · 1657 阅读 · 4 评论 -
cp12_实现a M ArtificialNN_gzip_mnist_struct_savez_compressed_fetch_openml_back propagation_weight更_L2
As you may know, deep learning is getting a lot of attention from the press and is without any doubt the hottest topic in the machine learning field. Deep learning can be understood as a subfield of machine learning that is concerned with training art...原创 2021-01-07 10:40:22 · 2110 阅读 · 0 评论 -
cp10_回归预测连续目标变量_boston_Residual_plot_mlxtend_sns_pd_covariance_correlation_RANSAC_R2_Ridge_C_F_A_K_树
Predicting Continuous Target Variables with Regression Analysis Throughout the previous cp9_Embedding aModel into a Web Application_pickle_sqlite3_Flask_wtforms_pythonanywhere_pickle_seria_Linli522362242的专栏-CSDN博客(cp9_Embedding a Model into a W...原创 2020-12-24 17:01:48 · 5151 阅读 · 1 评论 -
cp9_Embedding aModel into a Web Application_pickle_sqlite3_Flask_wtforms_pythonanywhere_pickle_seria
In the previous chapters, you learned about the many different machine learning concepts and algorithms that can help us with better and more efficient decision making.However, machine learning techniques are not limited to offline applications and a...原创 2020-12-16 16:57:13 · 1049 阅读 · 1 评论 -
cp8_Sentiment_urlretrieve_pyprind_tarfile_bag词袋_walk目录_regex_verbose_N-gram_Hash_colab_verbose_文本向量化
In the modern internet and social media age, people's opinions, reviews, and recommendations have become a valuable resource for political science and businesses. Thanks to modern technologies, we are now able to collect and analyze such data most eff...原创 2020-12-06 07:18:11 · 2184 阅读 · 1 评论 -
cp7_SelectModel_Ensemble Learning_MajorityVoteClassifier_weight_logistic_get_params_bagging_transAxe
In the previous chapter, we focused on the best practices for tuning and evaluating different models for classification. In this chapter, we will build upon those techniques and explore different methods for constructing a set of classifiers that can ...原创 2020-11-26 00:52:54 · 2116 阅读 · 0 评论 -
cp6_Model Eval_Confusion_Hyperpara Tuning_pipeline_variance_bias_ validation_learning curve_strength
In the previous chapters, you learned about the essential machine learning algorithms for classification and how to get our data into shape before we feed it into those algorithms. Now, it's time to learn about the best practices of building good mach...原创 2020-11-15 08:20:06 · 1866 阅读 · 0 评论 -
ValueError: Duplicate node name in graph: ‘ones‘ _Lambda
# x: input_shape=(batches_None, size_None, size_None, 3 anchors, 80 classes+5) # 5: tx,ty,tw,th, p0def yolo_boxes(pred, anchors, classes): # extraction # pred: (batch_size, grid, grid, anchors, (tx,ty, tw,th, objectness scores or p), ...classes ).原创 2020-09-27 18:56:21 · 2481 阅读 · 1 评论 -
14_3_CNN_dense_v1_v2_YOLO_meanAveragePrecision_mAP_bilinear_resize图_nn.Conv2DTranspose_dilation_flip
14_Deep Computer Vision Using Convolutional Neural Networks_pool_GridSpec:https://blog.csdn.net/Linli522362242/article/details/10830226614_Deep Computer Vision Using Convolutional Neural Networks_2_LeNet-5_ResNet-50_ran out of datahttps://blog.csdn.net/L原创 2021-03-15 05:38:17 · 1271 阅读 · 1 评论