{"id":3801,"date":"2022-04-18T10:30:53","date_gmt":"2022-04-18T02:30:53","guid":{"rendered":"http:\/\/139.9.1.231\/?p=3801"},"modified":"2022-04-18T10:31:15","modified_gmt":"2022-04-18T02:31:15","slug":"pytorch-22","status":"publish","type":"post","link":"http:\/\/139.9.1.231\/index.php\/2022\/04\/18\/pytorch-22\/","title":{"rendered":"\u795e\u7ecf\u7f51\u7edc\u548c\u76f8\u5173\u7b97\u6cd5\u7684\u7b80\u5355 PyTorch \u5b9e\u73b0"},"content":{"rendered":"\n<p class=\"has-light-pink-background-color has-background\">github\u5730\u5740\uff1a<\/p>\n\n\n\n<p class=\"has-light-pink-background-color has-background\"><a href=\"https:\/\/github.com\/labmlai\/annotated_deep_learning_paper_implementations\"><strong>https:\/\/github.com\/labmlai\/annotated_deep_learning_paper_implementations<\/strong><\/a><\/p>\n\n\n\n<p>\u8fd9\u662f\u795e\u7ecf\u7f51\u7edc\u548c\u76f8\u5173\u7b97\u6cd5\u7684\u7b80\u5355 PyTorch \u5b9e\u73b0\u7684\u96c6\u5408\u3002\u8fd9\u4e9b\u5b9e\u73b0\u4e0e\u89e3\u91ca\u4e00\u8d77\u8bb0\u5f55\uff0c<\/p>\n\n\n\n<p><a href=\"https:\/\/nn.labml.ai\/index.html\">\u8be5\u7f51\u7ad9<\/a>&nbsp;\u5c06\u8fd9\u4e9b\u5448\u73b0\u4e3a\u5e76\u6392\u683c\u5f0f\u5316\u7684\u6ce8\u91ca\u3002\u6211\u4eec\u76f8\u4fe1\u8fd9\u4e9b\u5c06\u5e2e\u52a9\u60a8\u66f4\u597d\u5730\u7406\u89e3\u8fd9\u4e9b\u7b97\u6cd5\u3002<\/p>\n\n\n\n<figure class=\"wp-block-image\"><a href=\"https:\/\/camo.githubusercontent.com\/c82d8f2a68e84e3b3355b46f96a388e28a55756a8a816f57ad4e95bbaed807ea\/68747470733a2f2f6e6e2e6c61626d6c2e61692f64716e2d6c696768742e706e67\" target=\"_blank\" rel=\"noreferrer noopener\"><img src=\"https:\/\/camo.githubusercontent.com\/c82d8f2a68e84e3b3355b46f96a388e28a55756a8a816f57ad4e95bbaed807ea\/68747470733a2f2f6e6e2e6c61626d6c2e61692f64716e2d6c696768742e706e67\" alt=\"\u622a\u5c4f\"\/><\/a><\/figure>\n\n\n\n<p>\u6211\u4eec\u51e0\u4e4e\u6bcf\u5468\u90fd\u5728\u79ef\u6781\u7ef4\u62a4\u8fd9\u4e2a repo \u5e76\u6dfb\u52a0\u65b0\u7684\u5b9e\u73b0\u3002&nbsp;<a href=\"https:\/\/twitter.com\/labmlai\"><\/a>\u66f4\u65b0\u3002<\/p>\n\n\n\n<h2><a href=\"https:\/\/github.com\/labmlai\/annotated_deep_learning_paper_implementations#modules\"><\/a>\u6a21\u5757:<\/h2>\n\n\n\n<h4>\u2728&nbsp;<a href=\"https:\/\/nn.labml.ai\/transformers\/index.html\">Transformers<\/a><\/h4>\n\n\n\n<ul><li><a href=\"https:\/\/nn.labml.ai\/transformers\/mha.html\">Multi-headed attention<\/a><\/li><li><a href=\"https:\/\/nn.labml.ai\/transformers\/models.html\">Transformer building blocks<\/a><\/li><li><a href=\"https:\/\/nn.labml.ai\/transformers\/xl\/index.html\">Transformer XL<\/a><ul><li><a href=\"https:\/\/nn.labml.ai\/transformers\/xl\/relative_mha.html\">Relative multi-headed attention<\/a><\/li><\/ul><\/li><li><a href=\"https:\/\/nn.labml.ai\/transformers\/rope\/index.html\">Rotary Positional Embeddings<\/a><\/li><li><a href=\"https:\/\/nn.labml.ai\/transformers\/retro\/index.html\">RETRO<\/a><\/li><li><a href=\"https:\/\/nn.labml.ai\/transformers\/compressive\/index.html\">Compressive Transformer<\/a><\/li><li><a href=\"https:\/\/nn.labml.ai\/transformers\/gpt\/index.html\">GPT Architecture<\/a><\/li><li><a href=\"https:\/\/nn.labml.ai\/transformers\/glu_variants\/simple.html\">GLU Variants<\/a><\/li><li><a href=\"https:\/\/nn.labml.ai\/transformers\/knn\">kNN-LM: Generalization through Memorization<\/a><\/li><li><a href=\"https:\/\/nn.labml.ai\/transformers\/feedback\/index.html\">Feedback Transformer<\/a><\/li><li><a href=\"https:\/\/nn.labml.ai\/transformers\/switch\/index.html\">Switch Transformer<\/a><\/li><li><a href=\"https:\/\/nn.labml.ai\/transformers\/fast_weights\/index.html\">Fast Weights Transformer<\/a><\/li><li><a href=\"https:\/\/nn.labml.ai\/transformers\/fnet\/index.html\">FNet<\/a><\/li><li><a href=\"https:\/\/nn.labml.ai\/transformers\/aft\/index.html\">Attention Free Transformer<\/a><\/li><li><a href=\"https:\/\/nn.labml.ai\/transformers\/mlm\/index.html\">Masked Language Model<\/a><\/li><li><a href=\"https:\/\/nn.labml.ai\/transformers\/mlp_mixer\/index.html\">MLP-Mixer: An all-MLP Architecture for Vision<\/a><\/li><li><a href=\"https:\/\/nn.labml.ai\/transformers\/gmlp\/index.html\">Pay Attention to MLPs (gMLP)<\/a><\/li><li><a href=\"https:\/\/nn.labml.ai\/transformers\/vit\/index.html\">Vision Transformer (ViT)<\/a><\/li><li><a href=\"https:\/\/nn.labml.ai\/transformers\/primer_ez\/index.html\">Primer EZ<\/a><\/li><li><a href=\"https:\/\/nn.labml.ai\/transformers\/hour_glass\/index.html\">Hourglass<\/a><\/li><\/ul>\n\n\n\n<h4><a href=\"https:\/\/github.com\/labmlai\/annotated_deep_learning_paper_implementations#-recurrent-highway-networks\"><\/a>\u2728&nbsp;<a href=\"https:\/\/nn.labml.ai\/recurrent_highway_networks\/index.html\">Recurrent Highway Networks<\/a><\/h4>\n\n\n\n<h4><a href=\"https:\/\/github.com\/labmlai\/annotated_deep_learning_paper_implementations#-lstm\"><\/a>\u2728&nbsp;<a href=\"https:\/\/nn.labml.ai\/lstm\/index.html\">LSTM<\/a><\/h4>\n\n\n\n<h4><a href=\"https:\/\/github.com\/labmlai\/annotated_deep_learning_paper_implementations#-hypernetworks---hyperlstm\"><\/a>\u2728&nbsp;<a href=\"https:\/\/nn.labml.ai\/hypernetworks\/hyper_lstm.html\">HyperNetworks &#8211; HyperLSTM<\/a><\/h4>\n\n\n\n<h4><a href=\"https:\/\/github.com\/labmlai\/annotated_deep_learning_paper_implementations#-resnet\"><\/a>\u2728&nbsp;<a href=\"https:\/\/nn.labml.ai\/resnet\/index.html\">ResNet<\/a><\/h4>\n\n\n\n<h4><a href=\"https:\/\/github.com\/labmlai\/annotated_deep_learning_paper_implementations#-convmixer\"><\/a>\u2728&nbsp;<a href=\"https:\/\/nn.labml.ai\/conv_mixer\/index.html\">ConvMixer<\/a><\/h4>\n\n\n\n<h4><a href=\"https:\/\/github.com\/labmlai\/annotated_deep_learning_paper_implementations#-capsule-networks\"><\/a>\u2728&nbsp;<a href=\"https:\/\/nn.labml.ai\/capsule_networks\/index.html\">Capsule Networks<\/a><\/h4>\n\n\n\n<h4><a href=\"https:\/\/github.com\/labmlai\/annotated_deep_learning_paper_implementations#-generative-adversarial-networks\"><\/a>\u2728&nbsp;<a href=\"https:\/\/nn.labml.ai\/gan\/index.html\">Generative Adversarial Networks<\/a><\/h4>\n\n\n\n<ul><li><a href=\"https:\/\/nn.labml.ai\/gan\/original\/index.html\">Original GAN<\/a><\/li><li><a href=\"https:\/\/nn.labml.ai\/gan\/dcgan\/index.html\">GAN with deep convolutional network<\/a><\/li><li><a href=\"https:\/\/nn.labml.ai\/gan\/cycle_gan\/index.html\">Cycle GAN<\/a><\/li><li><a href=\"https:\/\/nn.labml.ai\/gan\/wasserstein\/index.html\">Wasserstein GAN<\/a><\/li><li><a href=\"https:\/\/nn.labml.ai\/gan\/wasserstein\/gradient_penalty\/index.html\">Wasserstein GAN with Gradient Penalty<\/a><\/li><li><a href=\"https:\/\/nn.labml.ai\/gan\/stylegan\/index.html\">StyleGAN 2<\/a><\/li><\/ul>\n\n\n\n<h4><a href=\"https:\/\/github.com\/labmlai\/annotated_deep_learning_paper_implementations#-diffusion-models\"><\/a>\u2728&nbsp;<a href=\"https:\/\/nn.labml.ai\/diffusion\/index.html\">Diffusion models<\/a><\/h4>\n\n\n\n<ul><li><a href=\"https:\/\/nn.labml.ai\/diffusion\/ddpm\/index.html\">Denoising Diffusion Probabilistic Models (DDPM)<\/a><\/li><\/ul>\n\n\n\n<h4><a href=\"https:\/\/github.com\/labmlai\/annotated_deep_learning_paper_implementations#-sketch-rnn\"><\/a>\u2728&nbsp;<a href=\"https:\/\/nn.labml.ai\/sketch_rnn\/index.html\">Sketch RNN<\/a><\/h4>\n\n\n\n<h4><a href=\"https:\/\/github.com\/labmlai\/annotated_deep_learning_paper_implementations#-graph-neural-networks\"><\/a>\u2728&nbsp;Graph Neural Networks<\/h4>\n\n\n\n<ul><li><a href=\"https:\/\/nn.labml.ai\/graphs\/gat\/index.html\">Graph Attention Networks (GAT)<\/a><\/li><li><a href=\"https:\/\/nn.labml.ai\/graphs\/gatv2\/index.html\">Graph Attention Networks v2 (GATv2)<\/a><\/li><\/ul>\n\n\n\n<h4><a href=\"https:\/\/github.com\/labmlai\/annotated_deep_learning_paper_implementations#-counterfactual-regret-minimization-cfr\"><\/a>\u2728&nbsp;<a href=\"https:\/\/nn.labml.ai\/cfr\/index.html\">Counterfactual Regret Minimization (CFR)<\/a><\/h4>\n\n\n\n<p>Solving games with incomplete information such as poker with CFR.<\/p>\n\n\n\n<ul><li><a href=\"https:\/\/nn.labml.ai\/cfr\/kuhn\/index.html\">Kuhn Poker<\/a><\/li><\/ul>\n\n\n\n<h4><a href=\"https:\/\/github.com\/labmlai\/annotated_deep_learning_paper_implementations#-reinforcement-learning\"><\/a>\u2728&nbsp;<a href=\"https:\/\/nn.labml.ai\/rl\/index.html\">Reinforcement Learning<\/a><\/h4>\n\n\n\n<ul><li><a href=\"https:\/\/nn.labml.ai\/rl\/ppo\/index.html\">Proximal Policy Optimization<\/a>&nbsp;with&nbsp;<a href=\"https:\/\/nn.labml.ai\/rl\/ppo\/gae.html\">Generalized Advantage Estimation<\/a><\/li><li><a href=\"https:\/\/nn.labml.ai\/rl\/dqn\/index.html\">Deep Q Networks<\/a>&nbsp;with with&nbsp;<a href=\"https:\/\/nn.labml.ai\/rl\/dqn\/model.html\">Dueling Network<\/a>,&nbsp;<a href=\"https:\/\/nn.labml.ai\/rl\/dqn\/replay_buffer.html\">Prioritized Replay<\/a>&nbsp;and Double Q Network.<\/li><\/ul>\n\n\n\n<h4><a href=\"https:\/\/github.com\/labmlai\/annotated_deep_learning_paper_implementations#-optimizers\"><\/a>\u2728&nbsp;<a href=\"https:\/\/nn.labml.ai\/optimizers\/index.html\">Optimizers<\/a><\/h4>\n\n\n\n<ul><li><a href=\"https:\/\/nn.labml.ai\/optimizers\/adam.html\">Adam<\/a><\/li><li><a href=\"https:\/\/nn.labml.ai\/optimizers\/amsgrad.html\">AMSGrad<\/a><\/li><li><a href=\"https:\/\/nn.labml.ai\/optimizers\/adam_warmup.html\">Adam Optimizer with warmup<\/a><\/li><li><a href=\"https:\/\/nn.labml.ai\/optimizers\/noam.html\">Noam Optimizer<\/a><\/li><li><a href=\"https:\/\/nn.labml.ai\/optimizers\/radam.html\">Rectified Adam Optimizer<\/a><\/li><li><a href=\"https:\/\/nn.labml.ai\/optimizers\/ada_belief.html\">AdaBelief Optimizer<\/a><\/li><\/ul>\n\n\n\n<h4><a href=\"https:\/\/github.com\/labmlai\/annotated_deep_learning_paper_implementations#-normalization-layers\"><\/a>\u2728&nbsp;<a href=\"https:\/\/nn.labml.ai\/normalization\/index.html\">Normalization Layers<\/a><\/h4>\n\n\n\n<ul><li><a href=\"https:\/\/nn.labml.ai\/normalization\/batch_norm\/index.html\">Batch Normalization<\/a><\/li><li><a href=\"https:\/\/nn.labml.ai\/normalization\/layer_norm\/index.html\">Layer Normalization<\/a><\/li><li><a href=\"https:\/\/nn.labml.ai\/normalization\/instance_norm\/index.html\">Instance Normalization<\/a><\/li><li><a href=\"https:\/\/nn.labml.ai\/normalization\/group_norm\/index.html\">Group Normalization<\/a><\/li><li><a href=\"https:\/\/nn.labml.ai\/normalization\/weight_standardization\/index.html\">Weight Standardization<\/a><\/li><li><a href=\"https:\/\/nn.labml.ai\/normalization\/batch_channel_norm\/index.html\">Batch-Channel Normalization<\/a><\/li><li><a href=\"https:\/\/nn.labml.ai\/normalization\/deep_norm\/index.html\">DeepNorm<\/a><\/li><\/ul>\n\n\n\n<h4><a href=\"https:\/\/github.com\/labmlai\/annotated_deep_learning_paper_implementations#-distillation\"><\/a>\u2728&nbsp;<a href=\"https:\/\/nn.labml.ai\/distillation\/index.html\">Distillation<\/a><\/h4>\n\n\n\n<h4><a href=\"https:\/\/github.com\/labmlai\/annotated_deep_learning_paper_implementations#-adaptive-computation\"><\/a>\u2728&nbsp;<a href=\"https:\/\/nn.labml.ai\/adaptive_computation\/index.html\">Adaptive Computation<\/a><\/h4>\n\n\n\n<ul><li><a href=\"https:\/\/nn.labml.ai\/adaptive_computation\/ponder_net\/index.html\">PonderNet<\/a><\/li><\/ul>\n\n\n\n<h4><a href=\"https:\/\/github.com\/labmlai\/annotated_deep_learning_paper_implementations#-uncertainty\"><\/a>\u2728&nbsp;<a href=\"https:\/\/nn.labml.ai\/uncertainty\/index.html\">Uncertainty<\/a><\/h4>\n\n\n\n<ul><li><a href=\"https:\/\/nn.labml.ai\/uncertainty\/evidence\/index.html\">Evidential Deep Learning to Quantify Classification Uncertainty<\/a><\/li><\/ul>\n\n\n\n<h3><a href=\"https:\/\/github.com\/labmlai\/annotated_deep_learning_paper_implementations#installation\"><\/a>Installation<\/h3>\n\n\n\n<pre class=\"wp-block-preformatted\">pip install labml-nn<\/pre>\n","protected":false},"excerpt":{"rendered":"<p>github\u5730\u5740\uff1a https:\/\/github.com\/labmlai\/annotated_deep_lea &hellip; <a href=\"http:\/\/139.9.1.231\/index.php\/2022\/04\/18\/pytorch-22\/\" class=\"more-link\">\u7ee7\u7eed\u9605\u8bfb<span class=\"screen-reader-text\">\u795e\u7ecf\u7f51\u7edc\u548c\u76f8\u5173\u7b97\u6cd5\u7684\u7b80\u5355 PyTorch \u5b9e\u73b0<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[17,11,4],"tags":[],"_links":{"self":[{"href":"http:\/\/139.9.1.231\/index.php\/wp-json\/wp\/v2\/posts\/3801"}],"collection":[{"href":"http:\/\/139.9.1.231\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/139.9.1.231\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/139.9.1.231\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/139.9.1.231\/index.php\/wp-json\/wp\/v2\/comments?post=3801"}],"version-history":[{"count":4,"href":"http:\/\/139.9.1.231\/index.php\/wp-json\/wp\/v2\/posts\/3801\/revisions"}],"predecessor-version":[{"id":3805,"href":"http:\/\/139.9.1.231\/index.php\/wp-json\/wp\/v2\/posts\/3801\/revisions\/3805"}],"wp:attachment":[{"href":"http:\/\/139.9.1.231\/index.php\/wp-json\/wp\/v2\/media?parent=3801"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/139.9.1.231\/index.php\/wp-json\/wp\/v2\/categories?post=3801"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/139.9.1.231\/index.php\/wp-json\/wp\/v2\/tags?post=3801"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}