{"id":4347,"date":"2017-08-12T01:00:00","date_gmt":"2017-08-11T17:00:00","guid":{"rendered":"http:\/\/swarma.org\/%swarma-paper%\/"},"modified":"2018-12-05T22:07:30","modified_gmt":"2018-12-05T14:07:30","slug":"%e5%90%90%e8%a1%80%e6%95%b4%e7%90%86%ef%bc%9apytorch%e9%a1%b9%e7%9b%ae%e4%bb%a3%e7%a0%81%e4%b8%8e%e8%b5%84%e6%ba%90%e5%88%97%e8%a1%a8-%e8%b5%84%e6%ba%90%e4%b8%8b%e8%bd%bd","status":"publish","type":"post","link":"https:\/\/swarma.org\/?p=4347","title":{"rendered":"\u5410\u8840\u6574\u7406\uff1aPyTorch\u9879\u76ee\u4ee3\u7801\u4e0e\u8d44\u6e90\u5217\u8868 | \u8d44\u6e90\u4e0b\u8f7d"},"content":{"rendered":"
\n

\"\u96c6\u667a\"<\/p>\n

\n
\n
\n
\n
<\/section>\n<\/section>\n
\n
\n
\n

<\/span><\/p>\n

\u672c\u6587\u6536\u96c6\u4e86\u5927\u91cf\u57fa\u4e8e PyTorch \u5b9e\u73b0\u7684\u4ee3\u7801\u94fe\u63a5\uff0c<\/strong>\u5176\u4e2d\u6709\u9002\u7528\u4e8e\u6df1\u5ea6\u5b66\u4e60\u65b0\u624b\u7684\u201c\u5165\u95e8\u6307\u5bfc\u7cfb\u5217\u201d\uff0c\u4e5f\u6709\u9002\u7528\u4e8e\u8001\u53f8\u673a\u7684\u8bba\u6587\u4ee3\u7801\u5b9e\u73b0\uff0c\u5305\u62ec Attention Based CNN\u3001A3C\u3001WGAN\u7b49\u7b49\u3002\u6240\u6709\u4ee3\u7801\u5747\u6309\u7167\u6240\u5c5e\u6280\u672f\u9886\u57df\u5206\u7c7b<\/strong>\uff0c<\/strong>\u5305\u62ec\u673a\u5668\u89c6\u89c9\/\u56fe\u50cf\u76f8\u5173\u3001\u81ea\u7136\u8bed\u8a00\u5904\u7406\u76f8\u5173\u3001\u5f3a\u5316\u5b66\u4e60\u76f8\u5173\u7b49\u7b49\u3002\u6240\u4ee5\u5982\u679c\u4f60\u6253\u7b97\u5165\u624b\u8fd9\u98ce\u884c\u4e00\u4e16\u7684 PyTorch \u6280\u672f\uff0c\u90a3\u4e48\u5c31\u5feb\u5feb\u6536\u85cf\u672c\u6587\u5427\uff01<\/span><\/p>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n

\n
\n
\n
\n
\n

PyTorch \u662f\u4ec0\u4e48\uff1f<\/strong><\/p>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n

PyTorch\u5373 Torch \u7684 Python \u7248\u672c\u3002Torch \u662f\u7531 Facebook \u53d1\u5e03\u7684\u6df1\u5ea6\u5b66\u4e60\u6846\u67b6\uff0c\u56e0\u652f\u6301\u52a8\u6001\u5b9a\u4e49\u8ba1\u7b97\u56fe\uff0c\u76f8\u6bd4\u4e8e Tensorflow \u4f7f\u7528\u8d77\u6765\u66f4\u4e3a\u7075\u6d3b\u65b9\u4fbf\uff0c\u7279\u522b\u9002\u5408\u4e2d\u5c0f\u578b\u673a\u5668\u5b66\u4e60\u9879\u76ee\u548c\u6df1\u5ea6\u5b66\u4e60\u521d\u5b66\u8005\u3002\u4f46\u56e0\u4e3a Torch \u7684\u5f00\u53d1\u8bed\u8a00\u662fLua\uff0c\u5bfc\u81f4\u5b83\u5728\u56fd\u5185\u4e00\u76f4\u5f88\u5c0f\u4f17\u3002\u6240\u4ee5\uff0c\u5728\u5343\u547c\u4e07\u5524\u4e0b\uff0cPyTorch\u5e94\u8fd0\u800c\u751f\uff01PyTorch \u7ee7\u627f\u4e86 Troch \u7684\u7075\u6d3b\u7279\u6027\uff0c\u53c8\u4f7f\u7528\u5e7f\u4e3a\u6d41\u884c\u7684 Python \u4f5c\u4e3a\u5f00\u53d1\u8bed\u8a00\uff0c\u6240\u4ee5\u4e00\u7ecf\u63a8\u51fa\u5c31\u5e7f\u53d7\u6b22\u8fce\uff01<\/span><\/p>\n

<\/span><\/inherit><\/p>\n

\n
\n
\n
\n
\n

\u76ee\u5f55\uff1a<\/strong><\/p>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n

    \n
  1. \n

    \u5165\u95e8\u7cfb\u5217\u6559\u7a0b<\/strong><\/span><\/p>\n<\/li>\n

  2. \n

    \u5165\u95e8\u5b9e\u4f8b<\/span><\/strong><\/span><\/strong><\/span><\/p>\n<\/li>\n

  3. \n

    \u56fe\u50cf\u3001\u89c6\u89c9\u3001CNN\u76f8\u5173\u5b9e\u73b0<\/span><\/strong><\/span><\/strong><\/span><\/p>\n<\/li>\n

  4. \n

    \u5bf9\u6297\u751f\u6210\u7f51\u7edc\u3001\u751f\u6210\u6a21\u578b\u3001GAN\u76f8\u5173\u5b9e\u73b0<\/span><\/strong><\/span><\/strong><\/span><\/p>\n<\/li>\n

  5. \n

    \u673a\u5668\u7ffb\u8bd1\u3001\u95ee\u7b54\u7cfb\u7edf\u3001NLP\u76f8\u5173\u5b9e\u73b0<\/span><\/strong><\/span><\/strong><\/span><\/p>\n<\/li>\n

  6. \n

    \u5148\u8fdb\u89c6\u89c9\u63a8\u7406\u7cfb\u7edf<\/span><\/strong><\/span><\/strong><\/span><\/p>\n<\/li>\n

  7. \n

    \u6df1\u5ea6\u5f3a\u5316\u5b66\u4e60\u76f8\u5173\u5b9e\u73b0<\/span><\/strong><\/span><\/strong><\/span><\/p>\n<\/li>\n

  8. \n

    \u901a\u7528\u795e\u7ecf\u7f51\u7edc\u9ad8\u7ea7\u5e94\u7528<\/span><\/strong><\/span><\/strong><\/span><\/p>\n<\/li>\n<\/ol>\n

    <\/span><\/inherit><\/p>\n

    \n
    \n
    \n
    \n
    1<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n

    <\/inherit>\u5165\u95e8\u7cfb\u5217\u6559\u7a0b<\/span><\/strong><\/inherit><\/p>\n

    1.PyTorch Tutorials<\/span><\/strong><\/p>\n

    https:\/\/github.com\/MorvanZhou\/PyTorch-Tutorial.git<\/span><\/p>\n

    \u8457\u540d\u7684\u201c\u83ab\u70e6\u201dPyTorch\u7cfb\u5217\u6559\u7a0b\u7684\u6e90\u7801\u3002<\/span><\/p>\n


    <\/p>\n

    2.Deep Learning with PyTorch: a 60-minute blitz<\/span><\/strong><\/p>\n

    http:\/\/pytorch.org\/tutorials\/beginner\/deep_learning_60min_blitz.html<\/span><\/p>\n

    PyTorch\u5b98\u7f51\u63a8\u8350\u7684\u7531\u7f51\u53cb\u63d0\u4f9b\u768460\u5206\u949f\u6559\u7a0b\uff0c\u672c\u7cfb\u5217\u6559\u7a0b\u7684\u91cd\u70b9\u5728\u4e8e\u4ecb\u7ecdPyTorch\u7684\u57fa\u672c\u539f\u7406\uff0c\u5305\u62ec\u81ea\u52a8\u6c42\u5bfc\uff0c\u795e\u7ecf\u7f51\u7edc\uff0c\u4ee5\u53ca\u8bef\u5dee\u4f18\u5316API\u3002<\/span><\/p>\n


    <\/p>\n

    3.Simple examples to introduce PyTorch<\/span><\/strong><\/p>\n

    https:\/\/github.com\/jcjohnson\/pytorch-examples.git<\/span><\/p>\n

    \u7531\u7f51\u53cb\u63d0\u4f9b\u7684PyTorch\u6559\u7a0b\uff0c\u901a\u8fc7\u4e00\u4e9b\u5b9e\u4f8b\u7684\u65b9\u5f0f\uff0c\u8bb2\u89e3PyTorch\u7684\u57fa\u672c\u539f\u7406\u3002\u5185\u5bb9\u6d89\u53caNumpy\u3001\u81ea\u52a8\u6c42\u5bfc\u3001\u53c2\u6570\u4f18\u5316\u3001\u6743\u91cd\u5171\u4eab\u7b49\u3002<\/span><\/p>\n


    <\/span><\/p>\n

    \n
    \n
    \n
    \n
    \n
    2<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n

    \u5165\u95e8\u5b9e\u4f8b<\/span><\/strong><\/span><\/p>\n

    1.Ten minutes pyTorch Tutorial<\/span><\/strong><\/p>\n

    https:\/\/github.com\/SherlockLiao\/pytorch-beginner.git<\/span><\/p>\n

    \u77e5\u4e4e\u4e0a\u201c\u5341\u5206\u949f\u5b66\u4e60PyTorch\u201c\u7cfb\u5217\u6559\u7a0b\u7684\u6e90\u7801\u3002<\/span><\/p>\n


    <\/span><\/p>\n

    2.Official PyTorch Examples<\/span><\/strong><\/p>\n

    https:\/\/github.com\/pytorch\/examples<\/span><\/p>\n

    \u5b98\u65b9\u63d0\u4f9b\u7684\u5b9e\u4f8b\u6e90\u7801\uff0c\u5305\u62ec\u4ee5\u4e0b\u5185\u5bb9\uff1a<\/span><\/p>\n

      \n
    • \n

      MNIST Convnets<\/span><\/p>\n<\/li>\n<\/ul>\n

        \n
      • \n

        Word level Language Modeling using LSTM RNNs<\/span><\/p>\n<\/li>\n<\/ul>\n

          \n
        • \n

          Training Imagenet Classifiers with Residual Networks<\/span><\/p>\n<\/li>\n<\/ul>\n

            \n
          • \n

            Generative Adversarial Networks (DCGAN)<\/span><\/p>\n<\/li>\n<\/ul>\n

              \n
            • \n

              Variational Auto-Encoders<\/span><\/p>\n<\/li>\n<\/ul>\n

                \n
              • \n

                Superresolution using an efficient sub-pixel convolutional neural network<\/span><\/p>\n<\/li>\n<\/ul>\n

                  \n
                • \n

                  Hogwild training of shared ConvNets across multiple processes on MNIST<\/span><\/p>\n<\/li>\n<\/ul>\n

                    \n
                  • \n

                    Training a CartPole to balance in OpenAI Gym with actor-critic<\/span><\/p>\n<\/li>\n<\/ul>\n

                      \n
                    • \n

                      Natural Language Inference (SNLI) with GloVe vectors, LSTMs, and torchtext<\/span><\/p>\n<\/li>\n<\/ul>\n

                        \n
                      • \n

                        Time sequence prediction – create an LSTM to learn Sine waves<\/span><\/p>\n<\/li>\n<\/ul>\n


                        <\/span><\/p>\n

                        3.PyTorch Tutorial for Deep Learning Researchers<\/span><\/strong><\/p>\n

                        https:\/\/github.com\/yunjey\/pytorch-tutorial.git<\/span><\/p>\n

                        \u636e\u8bf4\u662f\u63d0\u4f9b\u7ed9\u6df1\u5ea6\u5b66\u4e60\u79d1\u7814\u8005\u4eec\u7684PyTorch\u6559\u7a0b\u2190_\u2190\u3002\u6559\u7a0b\u4e2d\u7684\u6bcf\u4e2a\u5b9e\u4f8b\u7684\u4ee3\u7801\u90fd\u63a7\u5236\u572830\u884c\u5de6\u53f3\uff0c\u7b80\u5355\u6613\u61c2\uff0c\u5185\u5bb9\u5982\u4e0b\uff1a<\/span><\/p>\n

                          \n
                        • \n

                          PyTorch Basics<\/span><\/p>\n<\/li>\n<\/ul>\n

                            \n
                          • \n

                            Linear Regression<\/span><\/p>\n<\/li>\n<\/ul>\n

                              \n
                            • \n

                              Logistic Regression<\/span><\/p>\n<\/li>\n<\/ul>\n

                                \n
                              • \n

                                Feedforward Neural Network<\/span><\/p>\n<\/li>\n<\/ul>\n

                                  \n
                                • \n

                                  Convolutional Neural Network<\/span><\/p>\n<\/li>\n<\/ul>\n

                                    \n
                                  • \n

                                    Deep Residual Network<\/span><\/p>\n<\/li>\n<\/ul>\n

                                      \n
                                    • \n

                                      Recurrent Neural Network<\/span><\/p>\n<\/li>\n<\/ul>\n

                                        \n
                                      • \n

                                        Bidirectional Recurrent Neural Network<\/span><\/p>\n<\/li>\n<\/ul>\n

                                          \n
                                        • \n

                                          Language Model (RNN-LM)<\/span><\/p>\n<\/li>\n<\/ul>\n

                                            \n
                                          • \n

                                            Generative Adversarial Network<\/span><\/p>\n<\/li>\n<\/ul>\n

                                              \n
                                            • \n

                                              Image Captioning (CNN-RNN)<\/span><\/p>\n<\/li>\n<\/ul>\n

                                                \n
                                              • \n

                                                Deep Convolutional GAN (DCGAN)<\/span><\/p>\n<\/li>\n<\/ul>\n

                                                  \n
                                                • \n

                                                  Variational Auto-Encoder<\/span><\/p>\n<\/li>\n<\/ul>\n

                                                    \n
                                                  • \n

                                                    Neural Style Transfer<\/span><\/p>\n<\/li>\n<\/ul>\n

                                                      \n
                                                    • \n

                                                      TensorBoard in PyTorch<\/span><\/p>\n<\/li>\n<\/ul>\n


                                                      <\/span><\/p>\n

                                                      4PyTorch-playground<\/span><\/strong><\/p>\n

                                                      https:\/\/github.com\/aaron-xichen\/pytorch-playground.git<\/span><\/p>\n

                                                      PyTorch\u521d\u5b66\u8005\u7684Playground\uff0c\u5728\u8fd9\u91cc\u9488\u5bf9\u4e00\u4e0b\u5e38\u7528\u7684\u6570\u636e\u96c6\uff0c\u5df2\u7ecf\u5199\u597d\u4e86\u4e00\u4e9b\u6a21\u578b\uff0c\u6240\u4ee5\u5927\u5bb6\u53ef\u4ee5\u76f4\u63a5\u62ff\u8fc7\u6765\u73a9\u73a9\u770b\uff0c\u76ee\u524d\u652f\u6301\u4ee5\u4e0b\u6570\u636e\u96c6\u7684\u6a21\u578b\u3002<\/span><\/p>\n

                                                        \n
                                                      • \n

                                                        mnist, svhn<\/span><\/p>\n<\/li>\n<\/ul>\n

                                                          \n
                                                        • \n

                                                          cifar10, cifar100<\/span><\/p>\n<\/li>\n<\/ul>\n

                                                            \n
                                                          • \n

                                                            stl10<\/span><\/p>\n<\/li>\n<\/ul>\n

                                                              \n
                                                            • \n

                                                              alexnet<\/span><\/p>\n<\/li>\n<\/ul>\n

                                                                \n
                                                              • \n

                                                                vgg16, vgg16_bn, vgg19, vgg19_bn<\/span><\/p>\n<\/li>\n<\/ul>\n

                                                                  \n
                                                                • \n

                                                                  resnet18, resnet34, resnet50, resnet101, resnet152<\/span><\/p>\n<\/li>\n<\/ul>\n

                                                                    \n
                                                                  • \n

                                                                    squeezenet_v0, squeezenet_v1<\/span><\/p>\n<\/li>\n<\/ul>\n

                                                                      \n
                                                                    • \n

                                                                      inception_v3<\/span><\/p>\n<\/li>\n<\/ul>\n


                                                                      <\/p>\n

                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      3<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n

                                                                      \u56fe\u50cf\u3001\u89c6\u89c9\u3001CNN\u76f8\u5173\u5b9e\u73b0<\/strong><\/span><\/p>\n

                                                                      1.PyTorch-FCN<\/span><\/strong><\/p>\n

                                                                      https:\/\/github.com\/wkentaro\/pytorch-fcn.git<\/span><\/p>\n

                                                                      FCN(Fully Convolutional Networks implemented) \u7684PyTorch\u5b9e\u73b0\u3002<\/span><\/p>\n


                                                                      <\/p>\n

                                                                      2.Attention Transfer<\/span><\/strong><\/p>\n

                                                                      https:\/\/github.com\/szagoruyko\/attention-transfer.git<\/span><\/p>\n

                                                                      \u8bba\u6587 “Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer” \u7684PyTorch\u5b9e\u73b0\u3002<\/span><\/p>\n


                                                                      <\/p>\n

                                                                      3.Wide ResNet model in PyTorch<\/span><\/strong><\/p>\n

                                                                      https:\/\/github.com\/szagoruyko\/functional-zoo.git<\/span><\/p>\n

                                                                      \u4e00\u4e2aPyTorch\u5b9e\u73b0\u7684 ImageNet Classification \u3002<\/span><\/p>\n


                                                                      <\/p>\n

                                                                      4.CRNN for image-based sequence recognition<\/span><\/strong><\/p>\n

                                                                      https:\/\/github.com\/bgshih\/crnn.git<\/span><\/p>\n

                                                                      \u8fd9\u4e2a\u662f Convolutional Recurrent Neural Network (CRNN) \u7684 PyTorch \u5b9e\u73b0\u3002CRNN \u7531\u4e00\u4e9bCNN\uff0cRNN\u548cCTC\u7ec4\u6210\uff0c\u5e38\u7528\u4e8e\u57fa\u4e8e\u56fe\u50cf\u7684\u5e8f\u5217\u8bc6\u522b\u4efb\u52a1\uff0c\u4f8b\u5982\u573a\u666f\u6587\u672c\u8bc6\u522b\u548cOCR\u3002<\/span><\/p>\n


                                                                      <\/p>\n

                                                                      5.Scaling the Scattering Transform: Deep Hybrid Networks<\/span><\/strong><\/p>\n

                                                                      https:\/\/github.com\/edouardoyallon\/pyscatwave.git<\/span><\/p>\n

                                                                      \u4f7f\u7528\u4e86\u201cscattering network\u201d\u7684CNN\u5b9e\u73b0\uff0c\u7279\u522b\u7684\u6784\u67b6\u63d0\u5347\u4e86\u7f51\u7edc\u7684\u6548\u679c\u3002<\/span><\/p>\n


                                                                      <\/p>\n

                                                                      6.Conditional Similarity Networks (CSNs)<\/span><\/strong><\/p>\n

                                                                      https:\/\/github.com\/andreasveit\/conditional-similarity-networks.git<\/span><\/p>\n

                                                                      \u300aConditional Similarity Networks\u300b\u7684PyTorch\u5b9e\u73b0\u3002<\/span><\/p>\n


                                                                      <\/p>\n

                                                                      7.Multi-style Generative Network for Real-time Transfer<\/span><\/strong><\/p>\n

                                                                      https:\/\/github.com\/zhanghang1989\/PyTorch-Style-Transfer.git<\/span><\/p>\n

                                                                      MSG-Net \u4ee5\u53ca Neural Style \u7684 PyTorch \u5b9e\u73b0\u3002<\/span><\/p>\n


                                                                      <\/p>\n

                                                                      8.Big batch training<\/span><\/strong><\/p>\n

                                                                      https:\/\/github.com\/eladhoffer\/bigBatch.git<\/span><\/p>\n

                                                                      \u300aTrain longer, generalize better: closing the generalization gap in large batch training of neural networks\u300b\u7684 PyTorch \u5b9e\u73b0\u3002<\/span><\/p>\n


                                                                      <\/p>\n

                                                                      9.CortexNet<\/span><\/strong><\/p>\n

                                                                      https:\/\/github.com\/e-lab\/pytorch-CortexNet.git<\/span><\/p>\n

                                                                      \u4e00\u4e2a\u4f7f\u7528\u89c6\u9891\u8bad\u7ec3\u7684\u9c81\u68d2\u9884\u6d4b\u6df1\u5ea6\u795e\u7ecf\u7f51\u7edc\u3002<\/span><\/p>\n


                                                                      <\/p>\n

                                                                      10.Neural Message Passing for Quantum Chemistry<\/span><\/strong><\/p>\n

                                                                      https:\/\/github.com\/priba\/nmp_qc.git<\/span><\/p>\n

                                                                      \u8bba\u6587\u300aNeural Message Passing for Quantum Chemistry\u300b\u7684PyTorch\u5b9e\u73b0\uff0c\u597d\u50cf\u662f\u8bb2\u8ba1\u7b97\u673a\u89c6\u89c9\u4e0b\u7684\u795e\u7ecf\u4fe1\u606f\u4f20\u9012\u3002<\/span><\/p>\n


                                                                      <\/span><\/p>\n

                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      4<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n

                                                                      \u5bf9\u6297\u751f\u6210\u7f51\u7edc\u3001\u751f\u6210\u6a21\u578b\u3001GAN\u76f8\u5173\u5b9e\u73b0<\/strong><\/span><\/p>\n

                                                                      1.Generative Adversarial Networks (GANs) in PyTorch<\/span><\/strong><\/p>\n

                                                                      https:\/\/github.com\/devnag\/pytorch-generative-adversarial-networks.git<\/span><\/p>\n

                                                                      \u4e00\u4e2a\u975e\u5e38\u7b80\u5355\u7684\u7531PyTorch\u5b9e\u73b0\u7684\u5bf9\u6297\u751f\u6210\u7f51\u7edc<\/span><\/p>\n


                                                                      <\/p>\n

                                                                      2.DCGAN & WGAN with Pytorch<\/span><\/strong><\/p>\n

                                                                      https:\/\/github.com\/chenyuntc\/pytorch-GAN.git<\/span><\/p>\n

                                                                      \u7531\u4e2d\u56fd\u7f51\u53cb\u5b9e\u73b0\u7684DCGAN\u548cWGAN\uff0c\u4ee3\u7801\u5f88\u7b80\u6d01\u3002<\/span><\/p>\n


                                                                      <\/p>\n

                                                                      3.Official Code for WGAN<\/span><\/strong><\/p>\n

                                                                      https:\/\/github.com\/martinarjovsky\/WassersteinGAN.git<\/span><\/p>\n

                                                                      WGAN\u7684\u5b98\u65b9PyTorch\u5b9e\u73b0\u3002<\/span><\/p>\n


                                                                      <\/p>\n

                                                                      4.DiscoGAN in PyTorch<\/span><\/strong><\/p>\n

                                                                      https:\/\/github.com\/carpedm20\/DiscoGAN-pytorch.git<\/span><\/p>\n

                                                                      \u300aLearning to Discover Cross-Domain Relations with Generative Adversarial Networks\u300b\u7684 PyTorch \u5b9e\u73b0\u3002<\/span><\/p>\n


                                                                      <\/p>\n

                                                                      5.Adversarial Generator-Encoder Network<\/span><\/strong><\/p>\n

                                                                      https:\/\/github.com\/DmitryUlyanov\/AGE.git<\/span><\/p>\n

                                                                      \u300aAdversarial Generator-Encoder Networks\u300b\u7684 PyTorch \u5b9e\u73b0\u3002<\/span><\/p>\n


                                                                      <\/p>\n

                                                                      6.CycleGAN and pix2pix in PyTorch<\/span><\/strong><\/p>\n

                                                                      https:\/\/github.com\/junyanz\/pytorch-CycleGAN-and-pix2pix.git<\/span><\/p>\n

                                                                      \u56fe\u5230\u56fe\u7684\u7ffb\u8bd1\uff0c\u8457\u540d\u7684 CycleGAN \u4ee5\u53ca pix2pix \u7684PyTorch \u5b9e\u73b0\u3002<\/span><\/p>\n


                                                                      <\/p>\n

                                                                      7.Weight Normalized GAN<\/span><\/strong><\/p>\n

                                                                      https:\/\/github.com\/stormraiser\/GAN-weight-norm.git<\/span><\/p>\n

                                                                      \u300aOn the Effects of Batch and Weight Normalization in Generative Adversarial Networks\u300b\u7684 PyTorch \u5b9e\u73b0\u3002<\/span><\/p>\n


                                                                      <\/span><\/p>\n

                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      5<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n

                                                                      \u673a\u5668\u7ffb\u8bd1\u3001\u95ee\u7b54\u7cfb\u7edf\u3001NLP\u76f8\u5173\u5b9e\u73b0<\/span><\/strong><\/span><\/inherit><\/p>\n<\/section>\n

                                                                      1.DeepLearningForNLPInPytorch<\/span><\/strong><\/p>\n

                                                                      https:\/\/github.com\/rguthrie3\/DeepLearningForNLPInPytorch.git<\/span><\/p>\n

                                                                      \u4e00\u5957\u4ee5 NLP \u4e3a\u4e3b\u9898\u7684 PyTorch \u57fa\u7840\u6559\u7a0b\u3002\u672c\u6559\u7a0b\u4f7f\u7528Ipython Notebook\u7f16\u5199\uff0c\u770b\u8d77\u6765\u5f88\u76f4\u89c2\uff0c\u65b9\u4fbf\u5b66\u4e60\u3002<\/span><\/p>\n


                                                                      <\/p>\n

                                                                      2.Practial Pytorch with Topic RNN & NLP<\/span><\/strong><\/p>\n

                                                                      https:\/\/github.com\/spro\/practical-pytorch<\/span><\/p>\n

                                                                      \u4ee5 RNN for NLP \u4e3a\u51fa\u53d1\u70b9\u7684 PyTorch \u57fa\u7840\u6559\u7a0b\uff0c\u5206\u4e3a\u201cRNNs for NLP\u201d\u548c\u201cRNNs for timeseries data\u201d\u4e24\u4e2a\u90e8\u5206\u3002<\/span><\/p>\n


                                                                      <\/p>\n

                                                                      3.PyOpenNMT: Open-Source Neural Machine Translation<\/span><\/strong><\/p>\n

                                                                      https:\/\/github.com\/OpenNMT\/OpenNMT-py.git<\/span><\/p>\n

                                                                      \u4e00\u5957\u7531PyTorch\u5b9e\u73b0\u7684\u673a\u5668\u7ffb\u8bd1\u7cfb\u7edf\u3002<\/span><\/p>\n


                                                                      <\/p>\n

                                                                      4.Deal or No Deal? End-to-End Learning for Negotiation Dialogues<\/span><\/strong><\/p>\n

                                                                      https:\/\/github.com\/facebookresearch\/end-to-end-negotiator.git<\/span><\/p>\n

                                                                      Facebook AI Research \u8bba\u6587\u300aDeal or No Deal? End-to-End Learning for Negotiation Dialogues\u300b\u7684 PyTorch \u5b9e\u73b0\u3002<\/span><\/p>\n


                                                                      <\/p>\n

                                                                      5.Attention is all you need: A Pytorch Implementation<\/span><\/strong><\/p>\n

                                                                      https:\/\/github.com\/jadore801120\/attention-is-all-you-need-pytorch.git<\/span><\/p>\n

                                                                      Google Research \u8457\u540d\u8bba\u6587\u300aAttention is all you need\u300b\u7684PyTorch\u5b9e\u73b0\u3002<\/span><\/p>\n


                                                                      <\/span><\/p>\n

                                                                      6.Improved Visual Semantic Embeddings<\/span><\/strong><\/p>\n

                                                                      https:\/\/github.com\/fartashf\/vsepp.git<\/span><\/p>\n

                                                                      \u4e00\u79cd\u4ece\u56fe\u50cf\u4e2d\u68c0\u7d22\u6587\u5b57\u7684\u65b9\u6cd5\uff0c\u6765\u81ea\u8bba\u6587\uff1a\u300aVSE++: Improved Visual-Semantic Embeddings\u300b\u3002<\/span><\/p>\n


                                                                      <\/p>\n

                                                                      7.Reading Wikipedia to Answer Open-Domain Questions<\/span><\/strong><\/p>\n

                                                                      https:\/\/github.com\/facebookresearch\/DrQA.git<\/span><\/p>\n

                                                                      \u4e00\u4e2a\u5f00\u653e\u9886\u57df\u95ee\u7b54\u7cfb\u7edfDrQA\u7684PyTorch\u5b9e\u73b0\u3002<\/span><\/p>\n


                                                                      <\/p>\n

                                                                      8.Structured-Self-Attentive-Sentence-Embedding<\/span><\/strong><\/p>\n

                                                                      https:\/\/github.com\/ExplorerFreda\/Structured-Self-Attentive-Sentence-Embedding.git<\/span><\/p>\n

                                                                      IBM \u4e0e MILA \u53d1\u8868\u7684\u300aA Structured Self-Attentive Sentence Embedding\u300b\u7684\u5f00\u6e90\u5b9e\u73b0\u3002<\/span><\/p>\n


                                                                      <\/span><\/p>\n

                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      6<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n

                                                                      \u5148\u8fdb\u89c6\u89c9\u63a8\u7406\u7cfb\u7edf<\/span><\/strong><\/span><\/inherit><\/p>\n<\/section>\n

                                                                      1.Visual Question Answering in Pytorch<\/span><\/strong><\/p>\n

                                                                      https:\/\/github.com\/Cadene\/vqa.pytorch.git<\/span><\/p>\n

                                                                      \u4e00\u4e2aPyTorch\u5b9e\u73b0\u7684\u4f18\u79c0\u89c6\u89c9\u63a8\u7406\u95ee\u7b54\u7cfb\u7edf\uff0c\u662f\u57fa\u4e8e\u8bba\u6587\u300aMUTAN: Multimodal Tucker Fusion for Visual Question Answering\u300b\u5b9e\u73b0\u7684\u3002\u9879\u76ee\u4e2d\u6709\u8be6\u7ec6\u7684\u914d\u7f6e\u4f7f\u7528\u65b9\u6cd5\u8bf4\u660e\u3002<\/span><\/p>\n


                                                                      <\/p>\n

                                                                      2.Clevr-IEP<\/span><\/strong><\/p>\n

                                                                      https:\/\/github.com\/facebookresearch\/clevr-iep.git<\/span><\/p>\n

                                                                      Facebook Research \u8bba\u6587\u300aInferring and Executing Programs for Visual Reasoning\u300b\u7684PyTorch\u5b9e\u73b0\uff0c\u8bb2\u7684\u662f\u4e00\u4e2a\u53ef\u4ee5\u57fa\u4e8e\u56fe\u7247\u8fdb\u884c\u5173\u7cfb\u63a8\u7406\u95ee\u7b54\u7684\u7f51\u7edc\u3002<\/span><\/p>\n

                                                                      <\/span><\/inherit><\/p>\n

                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      7<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n

                                                                      \u6df1\u5ea6\u5f3a\u5316\u5b66\u4e60\u76f8\u5173\u5b9e\u73b0<\/span><\/strong><\/span><\/inherit><\/p>\n<\/section>\n

                                                                      1.Deep Reinforcement Learning withpytorch & visdom <\/span><\/strong><\/p>\n

                                                                      https:\/\/github.com\/onlytailei\/pytorch-rl.git<\/span><\/p>\n

                                                                      \u591a\u79cd\u4f7f\u7528PyTorch\u5b9e\u73b0\u5f3a\u5316\u5b66\u4e60\u7684\u65b9\u6cd5\u3002<\/span><\/p>\n


                                                                      <\/p>\n

                                                                      2.Value Iteration Networks in PyTorch<\/span><\/strong><\/p>\n

                                                                      https:\/\/github.com\/onlytailei\/Value-Iteration-Networks-PyTorch.git<\/span><\/p>\n

                                                                      Value Iteration Networks (VIN) \u7684PyTorch\u5b9e\u73b0\u3002<\/span><\/p>\n


                                                                      <\/p>\n

                                                                      3.A3C in PyTorch<\/span><\/strong><\/p>\n

                                                                      https:\/\/github.com\/onlytailei\/A3C-PyTorch.git<\/span><\/p>\n

                                                                      Adavantage async Actor-Critic (A3C) \u7684PyTorch\u5b9e\u73b0\u3002<\/span><\/p>\n


                                                                      <\/span><\/p>\n

                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      8<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n

                                                                      \u901a\u7528\u795e\u7ecf\u7f51\u7edc\u9ad8\u7ea7\u5e94\u7528<\/span><\/strong><\/span><\/inherit><\/p>\n<\/section>\n

                                                                      1.PyTorch-meta-optimizer<\/span><\/strong><\/p>\n

                                                                      https:\/\/github.com\/ikostrikov\/pytorch-meta-optimizer.git<\/span><\/p>\n

                                                                      \u8bba\u6587\u300aLearning to learn by gradient descent by gradient descent\u300b\u7684PyTorch\u5b9e\u73b0\u3002<\/span><\/p>\n


                                                                      <\/p>\n

                                                                      2.OptNet: Differentiable Optimization as a Layer in Neural Networks<\/span><\/strong><\/p>\n

                                                                      https:\/\/github.com\/locuslab\/optnet.git<\/span><\/p>\n

                                                                      \u8bba\u6587\u300aDifferentiable Optimization as a Layer in Neural Networks\u300b\u7684PyTorch\u5b9e\u73b0\u3002<\/span><\/p>\n


                                                                      <\/p>\n

                                                                      3.Task-based End-to-end Model Learning<\/span><\/strong><\/p>\n

                                                                      https:\/\/github.com\/locuslab\/e2e-model-learning.git<\/span><\/p>\n

                                                                      \u8bba\u6587\u300aTask-based End-to-end Model Learning\u300b\u7684PyTorch\u5b9e\u73b0\u3002<\/span><\/p>\n


                                                                      <\/p>\n

                                                                      4.DiracNets<\/span><\/strong><\/p>\n

                                                                      https:\/\/github.com\/szagoruyko\/diracnets.git<\/span><\/p>\n

                                                                      \u4e0d\u4f7f\u7528\u201cSkip-Connections\u201d\u800c\u642d\u5efa\u7279\u522b\u6df1\u7684\u795e\u7ecf\u7f51\u7edc\u7684\u65b9\u6cd5\u3002<\/span><\/p>\n


                                                                      <\/span><\/p>\n

                                                                      5.ODIN: Out-of-Distribution Detector for Neural Networks<\/span><\/strong>
                                                                      <\/p>\n

                                                                      https:\/\/github.com\/ShiyuLiang\/odin-pytorch.git<\/span><\/p>\n

                                                                      \u8fd9\u662f\u4e00\u4e2a\u80fd\u591f\u68c0\u6d4b\u201c\u5206\u5e03\u4e0d\u8db3\u201d\uff08Out-of-Distribution)\u6837\u672c\u7684\u65b9\u6cd5\u7684PyTorch\u5b9e\u73b0\u3002\u5f53\u201ctrue positive rate\u201d\u4e3a95\uff05\u65f6\uff0c\u8be5\u65b9\u6cd5\u5c06DenseNet\uff08\u9002\u7528\u4e8eCIFAR-10\uff09\u7684\u201cfalse positive rate\u201d\u4ece34.7\uff05\u964d\u81f34.3\uff05\u3002<\/span><\/p>\n


                                                                      <\/p>\n

                                                                      6.Accelerate Neural Net Training by Progressively Freezing Layers<\/span><\/strong><\/p>\n

                                                                      https:\/\/github.com\/ajbrock\/FreezeOut.git<\/span><\/p>\n

                                                                      \u4e00\u79cd\u4f7f\u7528\u201cprogressively freezing layers\u201d\u6765\u52a0\u901f\u795e\u7ecf\u7f51\u7edc\u8bad\u7ec3\u7684\u65b9\u6cd5\u3002<\/span><\/p>\n


                                                                      <\/p>\n

                                                                      7.Efficient_densenet_pytorch<\/span><\/strong><\/p>\n

                                                                      https:\/\/github.com\/gpleiss\/efficient_densenet_pytorch.git<\/span><\/p>\n

                                                                      DenseNets\u7684PyTorch\u5b9e\u73b0\uff0c\u4f18\u5316\u4ee5\u8282\u7701GPU\u5185\u5b58\u3002<\/span><\/p>\n


                                                                      <\/span><\/p>\n

                                                                      \n

                                                                      \u611f\u89c9\u5fae\u4fe1\u6587\u7ae0\u67e5\u8be2\u4e0d\u65b9\u4fbf\uff1f<\/span><\/p>\n

                                                                      \u5fae\u4fe1\u516c\u4f17\u53f7\u540e\u53f0\u56de\u590d\uff1a\u8d44\u6e90<\/span><\/strong><\/p>\n

                                                                      \u53ef\u4ee5\u627e\u5230\u672c\u6587PDF\u548cHTML\u7248\u7684\u4e0b\u8f7d\u94fe\u63a5\u54e6\uff01<\/span><\/p>\n

                                                                      \uff08\u901a\u8fc7\u8fde\u63a5\u627e\u5230\u8d44\u6599\u4e0b\u8f7d<\/strong>\u5373\u53ef\uff09<\/span><\/p>\n

                                                                      \u81ea\u5b66\u5bb9\u6613\u8d70\u5f2f\u8def\uff1f<\/span><\/p>\n

                                                                      \u5feb\u6765\u8ddf\u5f20\u6c5f\u6559\u6388\u5b66\u4e60\u6df1\u5ea6\u5b66\u4e60&PyTorch\u5427\uff01<\/span><\/p>\n

                                                                      \"\u96c6\u667a\"<\/div>\n

                                                                      \u672c\u8bfe\u7a0b\u5f3a\u5927\u7684\u52a9\u6559\u56e2\u961f<\/span><\/strong>
                                                                      <\/span><\/p>\n

                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \"\u96c6\u667a\"<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n

                                                                      \u674e\u5468\u56ed<\/strong><\/span><\/p>\n

                                                                      \u6e05\u534e\u5927\u5b66\u535a\u58eb\u3001\u8377\u5170Wageningen\u5927\u5b66WIMEK\u5b66\u8005\uff0c\u9065\u611f\u6570\u636e\u6316\u6398\u65b9\u5411\u3002<\/p>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n

                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \"\u96c6\u667a\"<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n

                                                                      \u80e1\u80dc<\/strong><\/span><\/p>\n

                                                                      \u4e2d\u56fd\u5730\u8d28\u5927\u5b66\uff08\u6b66\u6c49\uff09\u7855\u58eb\u3001\u653b\u8bfb\u535a\u58eb\uff0c\u7a7a\u95f4\u6570\u636e\u6316\u6398\u548c\u667a\u6167\u4ea4\u901a\u65b9\u5411\uff0c\u719f\u6089Python\u8bed\u8a00\u3002<\/p>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n

                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \"\u96c6\u667a\"<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n

                                                                      \u5b59\u9896\u5b9d<\/span><\/strong><\/p>\n

                                                                      \u8377\u5170Wageningen\u5927\u5b66\u9065\u611f\u4e0e\u5730\u7406\u4fe1\u606f\u5b9e\u9a8c\u5ba4\u7814\u7a76\u751f\uff0c\u719f\u6089R\u3001Python\u8bed\u8a00\u3002<\/p>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n

                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \"\u96c6\u667a\"<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n

                                                                      \u82cf\u5c1a\u541b<\/span><\/strong><\/p>\n

                                                                       \u524d\u8fd0\u7ef4\u5f00\u53d1\u5de5\u7a0b\u5e08\u3001\u73b0Udacity\u673a\u5668\u5b66\u4e60\u8bfe\u7a0b\u52a9\u6559\uff0c\u719f\u6089Python\u8bed\u8a00\uff0cGitHub\u7528\u6237\u3001\u6709\u201c\u7b80\u4e66\u201d\u6280\u672f\u4e13\u680f\u3002<\/p>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n

                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \"\u96c6\u667a\"<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n

                                                                      \u4efb\u4f1f<\/span><\/strong><\/p>\n

                                                                      \u4e2d\u56fd\u79d1\u5b66\u9662\u5927\u5b66\u535a\u58eb\uff0c\u6c14\u5019\u7cfb\u7edf\u4e0e\u78b3\u5faa\u73af\u65b9\u5411\uff0c\u6709\u6df1\u5ea6\u5b66\u4e60\u6280\u672f\u57fa\u7840\uff0c\u719f\u6089\u6570\u636e\u6316\u6398\u4e0e\u7a7a\u95f4\u5206\u6790\u3002<\/p>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n

                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \"\u96c6\u667a\"<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n

                                                                      \u5f20\u5e86\u9038<\/p>\n

                                                                      \u5b66\u751f\uff0c\u6709\u7f16\u7a0b\u5de5\u4f5c\u7ecf\u9a8c\uff0c\u4e86\u89e3Python\u8bed\u8a00\u3002<\/p>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n


                                                                      <\/span><\/strong><\/span><\/p>\n

                                                                      \u6253\u5305\u7ec4\u8bfe\u53ea\u9700499\uffe5<\/span><\/strong><\/span><\/p>\n

                                                                      \u53ef\u5f00\u53d1\u7968<\/span><\/strong><\/span><\/p>\n

                                                                      \u56e2\u8d2d\u4eab\u4f18\u60e0<\/span><\/strong><\/span><\/p>\n

                                                                      \n

                                                                      \"\u96c6\u667a\"
                                                                      <\/p>\n

                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n

                                                                      \u96c6\u667aQQ\u7fa4\uff5c292641157
                                                                      \u5546\u52a1\u5408\u4f5c\uff5czhangqian@swarma.org
                                                                      \u6295\u7a3f\u8f6c\u8f7d\uff5cwangting@swarma.org<\/span><\/strong><\/p>\n

                                                                      \n

                                                                      \u25c6 <\/span>\u25c6 <\/span>\u25c6<\/span><\/span><\/strong><\/strong><\/h1>\n<\/section>\n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n
                                                                      \n

                                                                      \u641c\u7d22\u516c\u4f17\u53f7\uff1a\u96c6\u667a\u4ff1\u4e50\u90e8<\/span><\/strong><\/span><\/p>\n


                                                                      <\/span><\/strong><\/span><\/p>\n

                                                                      \u52a0\u5165\u201c\u6ca1\u6709\u56f4\u5899\u7684\u7814\u7a76\u6240\u201d<\/span><\/strong><\/span><\/p>\n

                                                                      \n

                                                                      \"\u96c6\u667a\"<\/p>\n<\/section>\n

                                                                      \u8ba9\u82f9\u679c\u7838\u5f97\u66f4\u731b\u70c8\u4e9b\u5427\uff01<\/span><\/p>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n

                                                                      \n

                                                                      \u59cb\u53d1\u4e8e\u5fae\u4fe1\u516c\u4f17\u53f7\uff1a \u96c6\u667a\u4ff1\u4e50\u90e8 <\/p>\n<\/blockquote>\n<\/div>\n","protected":false},"excerpt":{"rendered":"

                                                                      \u672c\u6587\u6536\u96c6\u4e86\u5927\u91cf\u57fa\u4e8e PyTorch \u5b9e\u73b0\u7684\u4ee3\u7801\u94fe\u63a5\uff0c\u5176\u4e2d\u6709\u9002\u7528\u4e8e\u6df1\u5ea6\u5b66\u4e60\u65b0\u624b\u7684\u201c\u5165\u95e8\u6307\u5bfc\u7cfb\u5217\u201d\uff0c\u4e5f\u6709\u9002\u7528\u4e8e\u8001\u53f8\u673a\u7684\u8bba\u6587\u4ee3\u7801\u5b9e\u73b0\uff0c\u5305\u62ec Attention Based CNN\u3001A3C\u3001WGAN\u7b49\u7b49\u3002\u6240\u6709\u4ee3\u7801\u5747\u6309\u7167\u6240\u5c5e\u6280\u672f\u9886\u57df\u5206\u7c7b\uff0c\u5305\u62ec\u673a\u5668\u89c6\u89c9\/\u56fe\u50cf\u76f8\u5173\u3001\u81ea\u7136\u8bed\u8a00\u5904\u7406\u76f8\u5173\u3001\u5f3a\u5316\u5b66\u4e60\u76f8\u5173\u7b49\u7b49\u3002\u6240\u4ee5\u5982\u679c\u4f60\u6253…<\/p>\n","protected":false},"author":1,"featured_media":4348,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[19],"tags":[],"special":[],"_links":{"self":[{"href":"https:\/\/swarma.org\/index.php?rest_route=\/wp\/v2\/posts\/4347"}],"collection":[{"href":"https:\/\/swarma.org\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/swarma.org\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/swarma.org\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/swarma.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=4347"}],"version-history":[{"count":1,"href":"https:\/\/swarma.org\/index.php?rest_route=\/wp\/v2\/posts\/4347\/revisions"}],"predecessor-version":[{"id":4369,"href":"https:\/\/swarma.org\/index.php?rest_route=\/wp\/v2\/posts\/4347\/revisions\/4369"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/swarma.org\/index.php?rest_route=\/wp\/v2\/media\/4348"}],"wp:attachment":[{"href":"https:\/\/swarma.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=4347"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/swarma.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=4347"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/swarma.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=4347"},{"taxonomy":"special","embeddable":true,"href":"https:\/\/swarma.org\/index.php?rest_route=%2Fwp%2Fv2%2Fspecial&post=4347"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}