{"id":371,"date":"2022-02-25T20:32:04","date_gmt":"2022-02-25T12:32:04","guid":{"rendered":"https:\/\/scutvk.cn\/?p=371"},"modified":"2022-02-25T20:32:04","modified_gmt":"2022-02-25T12:32:04","slug":"tabulardataset%ef%bc%8c%e4%bb%8e%e6%95%b0%e6%8d%ae%e9%9b%86%e5%88%b0%e5%90%91%e9%87%8f%e7%9a%84%e6%b5%81%e7%a8%8b","status":"publish","type":"post","link":"https:\/\/scutvk.cn\/?p=371","title":{"rendered":"TabularDataset\uff0c\u4ece\u6570\u636e\u96c6\u5230\u5411\u91cf\u7684\u6d41\u7a0b"},"content":{"rendered":"\n<p>\u524d\u8a00\uff1a\u5728\u5c1d\u8bd5\u624b\u6253\u4e00\u4e2a\u65b0\u95fb\u5206\u7c7b\u6a21\u578b\u7684\u65f6\u5019\uff0c\u53c2\u8003\u7f51\u4e0a\u7684\u4e00\u4e9b\u5f00\u6e90\u9879\u76ee\uff0c\u5176\u4e2d\u7ecf\u5e38\u6709\u7528\u5230TabularDataset\u8fd9\u4e2a\u7c7b\uff0c\u800c\u65e0\u8bba\u662f\u6e90\u7801\u6ce8\u91ca\u8fd8\u662f\u7f51\u4e0a\u535a\u5ba2\u5bf9\u8fd9\u4e2a\u7c7b\u7684\u89e3\u6790\u90fd\u5c11\u4e4b\u53c8\u5c11\u3002\u6b64blog\u4ee5\u8bb0\u5f55\u5728\u8fd9\u91cc\u7684\u4e00\u4e2a\u6316\u6398\u7ecf\u9a8c\u3001\u7ed3\u679c\u3002<\/p>\n\n\n\n<p>\u5e93\u5f15\u7528\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-preformatted\">import torch\nimport config as c # \u672c\u5730\u76ee\u5f55\u4e0bpy\u811a\u672c\uff0c\u4e0d\u662f\u7cfb\u7edf\u5e93\nfrom torchtext.legacy.data import Field, TabularDatase\nfrom torchtext.vocab import Vectors<\/pre>\n\n\n\n<p>\u5c40\u90e8\u6e90\u7801\uff1a(\u90e8\u5206\u6e90\u7801\uff0c\u65e0\u6cd5\u8fd0\u884c\uff0c\u4ec5\u4f9b\u53c2\u8003)<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>def load():\r\n    # \u521b\u5efaField\u5bf9\u8c61\r\n    TEXT = Field(sequential=True, tokenize=jiebatokenize)\r\n    LABEL = Field(sequential=False, dtype=torch.int64)\r\n\r\n    # \u8bfb\u53d6\u6570\u636e\r\n    traindataset, valdataset, testdataset = TabularDataset.splits(\r\n        path='..\/data',\r\n        train='cnews.train.txt',\r\n        validation='cnews.val.txt',\r\n        test='cnews.test.txt',\r\n        format='tsv',\r\n        fields=&#91;('Label', LABEL), ('Text', TEXT)]\r\n    )\r\n    \r\n    #\u8bfb\u53d6\u8bcd\u5411\u91cf\r\n    wordvectors = Vectors(name='..\/data\/sgns.sogounews.bigram-char_3')\r\n\r\n    #\u5efa\u7acb\u8bcd\u8868\r\n    TEXT.build_vocab(traindataset, valdataset, testdataset, vectors=wordvectors)\r\n    LABEL.build_vocab(traindataset, valdataset, testdataset)\r\n\r\n    config = c.Config(vocabulary_length=len(TEXT.vocab),\r\n                      embedding_dimension=TEXT.vocab.vectors.size()&#91;-1],\r\n                      wordvectors=TEXT.vocab.vectors,\r\n                      classesnumber=len(LABEL.vocab)\r\n                      )\r\n\r\n    return traindataset, valdataset, testdataset, config<\/code><\/pre>\n\n\n\n<p>TabularDataset\u8fd9\u4e2a\u7c7b\u6765\u81eatorchtext.legacy.data\uff0c\u5728torchtext\u7684\u5b98\u65b9\u6587\u6863\u4e2d\u5199\u6709\u662fLua torch\u7684\u79fb\u690d\u5e93\uff0c\u627e\u4e0d\u5230\u76f8\u5173\u6587\u6863\uff0c\u90a3\u6211\u4eec\u53ea\u80fd\u624b\u52a8\u8c03\u8bd5\u770b\u770b\u5b83\u7684\u7ed3\u6784\u5982\u4f55\uff1a\uff08\u6ce8\u610f\uff1a\u4e0b\u56fe\u4e2d\u7684traindata\u4e0e\u4e0a\u6587\u6e90\u7801traindataset\u662f\u540c\u4e00\u4e2a\u5bf9\u8c61\uff0c\u800c\u4e0b\u6587\u7684traindataset\u662f\u52a0\u5165\u4e86\u8fed\u4ee3\u5668\uff09<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" loading=\"lazy\" width=\"1024\" height=\"104\" src=\"https:\/\/x2.mday.top\/wp-content\/uploads\/2022\/02\/image-1-1024x104.png\" alt=\"\" class=\"wp-image-372\" srcset=\"https:\/\/scutvk.cn\/wp-content\/uploads\/2022\/02\/image-1-1024x104.png 1024w, https:\/\/scutvk.cn\/wp-content\/uploads\/2022\/02\/image-1-300x30.png 300w, https:\/\/scutvk.cn\/wp-content\/uploads\/2022\/02\/image-1-768x78.png 768w, https:\/\/scutvk.cn\/wp-content\/uploads\/2022\/02\/image-1-1536x156.png 1536w, https:\/\/scutvk.cn\/wp-content\/uploads\/2022\/02\/image-1-769x78.png 769w, https:\/\/scutvk.cn\/wp-content\/uploads\/2022\/02\/image-1.png 1736w\" sizes=\"(max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n\n\n\n<p>field\u4e2d\u53ef\u4ee5\u770b\u5230\u6211\u4eec\u4e4b\u524d\u6dfb\u52a0\u7684Field\uff0c\u4f3c\u4e8e\u7528\u5728\u9884\u5904\u7406\uff0c\u53ef\u4ee5\u770b\u89c1\u6211\u4eec\u8bbe\u7f6e\u7684torch.int64\u7684dtype<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" loading=\"lazy\" width=\"1024\" height=\"429\" src=\"https:\/\/x2.mday.top\/wp-content\/uploads\/2022\/02\/image-2-1024x429.png\" alt=\"\" class=\"wp-image-373\" srcset=\"https:\/\/scutvk.cn\/wp-content\/uploads\/2022\/02\/image-2-1024x429.png 1024w, https:\/\/scutvk.cn\/wp-content\/uploads\/2022\/02\/image-2-300x126.png 300w, https:\/\/scutvk.cn\/wp-content\/uploads\/2022\/02\/image-2-768x322.png 768w, https:\/\/scutvk.cn\/wp-content\/uploads\/2022\/02\/image-2-769x322.png 769w, https:\/\/scutvk.cn\/wp-content\/uploads\/2022\/02\/image-2.png 1121w\" sizes=\"(max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n\n\n\n<p>\u800cexamples\u5219\u662f\u6211\u4eec\u5728\u4ed6\u4eec\u4e4b\u4e2d\u5b58\u653e\u7684\u6570\u636e\uff0c\u65e0\u8bba\u662fLabel\u8fd8\u662fText\u90fd\u662fstr\u7c7b\u578b\uff0c\u5e76\u4e0d\u662f\u52a0\u5165Field\u540e\u4fbf\u6539\u53d8<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" loading=\"lazy\" width=\"1024\" height=\"210\" src=\"https:\/\/x2.mday.top\/wp-content\/uploads\/2022\/02\/image-3-1024x210.png\" alt=\"\" class=\"wp-image-374\" srcset=\"https:\/\/scutvk.cn\/wp-content\/uploads\/2022\/02\/image-3-1024x210.png 1024w, https:\/\/scutvk.cn\/wp-content\/uploads\/2022\/02\/image-3-300x62.png 300w, https:\/\/scutvk.cn\/wp-content\/uploads\/2022\/02\/image-3-768x158.png 768w, https:\/\/scutvk.cn\/wp-content\/uploads\/2022\/02\/image-3-769x158.png 769w, https:\/\/scutvk.cn\/wp-content\/uploads\/2022\/02\/image-3.png 1364w\" sizes=\"(max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n\n\n\n<p>\u4ece\u8fed\u4ee3\u5668\u91cc\u9762\u63d0\u53d6<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>for batches in traindataset:\n        texts = batches.Text\n        labels = batches.Label\n\n&lt;\u7565>\n\n\n        module_output = TextCNN(texts)\r\n<\/code><\/pre>\n\n\n\n<p>\u63d0\u53d6\u4e4b\u540e\u7684\uff0c\u65e0\u8bba\u662ftexts\u8fd8\u662flables\u90fd\u662fTensor\u6570\u7ec4\uff0c\u5728\u8fd9\u4e2a\u8fc7\u7a0b\u53ef\u80fd\u4fbf\u662f\u4ecestr\u5230Tensor\u7684\u8fc7\u7a0b\u4e86<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" loading=\"lazy\" width=\"1024\" height=\"275\" src=\"https:\/\/x2.mday.top\/wp-content\/uploads\/2022\/02\/image-4-1024x275.png\" alt=\"\" class=\"wp-image-375\" srcset=\"https:\/\/scutvk.cn\/wp-content\/uploads\/2022\/02\/image-4-1024x275.png 1024w, https:\/\/scutvk.cn\/wp-content\/uploads\/2022\/02\/image-4-300x81.png 300w, https:\/\/scutvk.cn\/wp-content\/uploads\/2022\/02\/image-4-768x206.png 768w, https:\/\/scutvk.cn\/wp-content\/uploads\/2022\/02\/image-4-769x206.png 769w, https:\/\/scutvk.cn\/wp-content\/uploads\/2022\/02\/image-4.png 1371w\" sizes=\"(max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n\n\n\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" loading=\"lazy\" width=\"1024\" height=\"179\" src=\"https:\/\/x2.mday.top\/wp-content\/uploads\/2022\/02\/image-5-1024x179.png\" alt=\"\" class=\"wp-image-376\" srcset=\"https:\/\/scutvk.cn\/wp-content\/uploads\/2022\/02\/image-5-1024x179.png 1024w, https:\/\/scutvk.cn\/wp-content\/uploads\/2022\/02\/image-5-300x52.png 300w, https:\/\/scutvk.cn\/wp-content\/uploads\/2022\/02\/image-5-768x134.png 768w, https:\/\/scutvk.cn\/wp-content\/uploads\/2022\/02\/image-5-769x134.png 769w, https:\/\/scutvk.cn\/wp-content\/uploads\/2022\/02\/image-5.png 1363w\" sizes=\"(max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n\n\n\n<p>\u518d\u5230\u540e\u9762\uff0c\u6765\u5230\u4e86\u6a21\u578b\u91cc\u9762<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>x = self.embedding(x)<\/code><\/pre>\n\n\n\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" loading=\"lazy\" width=\"1024\" height=\"158\" src=\"https:\/\/x2.mday.top\/wp-content\/uploads\/2022\/02\/image-6-1024x158.png\" alt=\"\" class=\"wp-image-378\" srcset=\"https:\/\/scutvk.cn\/wp-content\/uploads\/2022\/02\/image-6-1024x158.png 1024w, https:\/\/scutvk.cn\/wp-content\/uploads\/2022\/02\/image-6-300x46.png 300w, https:\/\/scutvk.cn\/wp-content\/uploads\/2022\/02\/image-6-768x118.png 768w, https:\/\/scutvk.cn\/wp-content\/uploads\/2022\/02\/image-6-1536x237.png 1536w, https:\/\/scutvk.cn\/wp-content\/uploads\/2022\/02\/image-6-769x119.png 769w, https:\/\/scutvk.cn\/wp-content\/uploads\/2022\/02\/image-6.png 1718w\" sizes=\"(max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n\n\n\n<p>\u6b64\u65f6\uff0c\u624d\u771f\u6b63\u53d8\u6210\u5411\u91cf<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u524d\u8a00\uff1a\u5728\u5c1d\u8bd5\u624b\u6253\u4e00\u4e2a\u65b0\u95fb\u5206\u7c7b\u6a21\u578b\u7684\u65f6\u5019\uff0c\u53c2\u8003\u7f51\u4e0a\u7684&hellip;<\/p>\n","protected":false},"author":1,"featured_media":373,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"jetpack_publicize_message":"","jetpack_is_tweetstorm":false,"jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":false,"jetpack_social_options":{"image_generator_settings":{"template":"highway","enabled":false}}},"categories":[10,12,2],"tags":[],"jetpack_publicize_connections":[],"jetpack_featured_media_url":"https:\/\/scutvk.cn\/wp-content\/uploads\/2022\/02\/image-2.png","_links":{"self":[{"href":"https:\/\/scutvk.cn\/index.php?rest_route=\/wp\/v2\/posts\/371"}],"collection":[{"href":"https:\/\/scutvk.cn\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/scutvk.cn\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/scutvk.cn\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/scutvk.cn\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=371"}],"version-history":[{"count":2,"href":"https:\/\/scutvk.cn\/index.php?rest_route=\/wp\/v2\/posts\/371\/revisions"}],"predecessor-version":[{"id":379,"href":"https:\/\/scutvk.cn\/index.php?rest_route=\/wp\/v2\/posts\/371\/revisions\/379"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/scutvk.cn\/index.php?rest_route=\/wp\/v2\/media\/373"}],"wp:attachment":[{"href":"https:\/\/scutvk.cn\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=371"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/scutvk.cn\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=371"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/scutvk.cn\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=371"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}