\u5728linux\u7cfb\u7edf\u4e0a\u4f7f\u7528\u8fdb\u884c\u795e\u7ecf\u7f51\u7edc\u5f00\u53d1\u7684\u914d\u7f6e\u65b9\u6cd5<\/p>\n
\u968f\u7740\u4eba\u5de5\u667a\u80fd\u548c\u6df1\u5ea6\u5b66\u4e60\u7684\u5feb\u901f\u53d1\u5c55\uff0c\u795e\u7ecf\u7f51\u7edc\u6210\u4e3a\u4e86\u4e00\u4e2a\u70ed\u95e8\u7684\u7814\u7a76\u9886\u57df\u3002PyCharm\u4f5c\u4e3a\u4e00\u6b3e\u5f3a\u5927\u7684Python\u96c6\u6210\u5f00\u53d1\u73af\u5883\uff0c\u53ef\u4ee5\u4e3a\u795e\u7ecf\u7f51\u7edc\u5f00\u53d1\u63d0\u4f9b\u4fbf\u6377\u800c\u9ad8\u6548\u7684\u5de5\u5177\u548c\u529f\u80fd\u3002\u672c\u6587\u5c06\u4ecb\u7ecd\u5728linux\u7cfb\u7edf\u4e0a\u4f7f\u7528pycharm\u8fdb\u884c\u795e\u7ecf\u7f51\u7edc\u5f00\u53d1\u7684\u914d\u7f6e\u65b9\u6cd5\uff0c\u5e76\u63d0\u4f9b\u4ee3\u7801\u793a\u4f8b\u3002<\/p>\n
\u6b65\u9aa41\uff1a\u5b89\u88c5PyCharm<\/p>\n
\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u4e0b\u8f7d\u548c\u5b89\u88c5PyCharm\u3002\u60a8\u53ef\u4ee5\u5728JetBrains\u7684\u5b98\u65b9\u7f51\u7ad9\u4e0a\u627e\u5230PyCharm\u7684\u6700\u65b0\u7248\u672c\u3002\u9009\u62e9\u9002\u7528\u4e8eLinux\u7cfb\u7edf\u7684\u7248\u672c\uff0c\u5e76\u6309\u7167\u5b98\u65b9\u7684\u5b89\u88c5\u6307\u5357\u8fdb\u884c\u5b89\u88c5\u3002\u5b89\u88c5\u5b8c\u6210\u540e\uff0c\u542f\u52a8PyCharm\u3002<\/p>\n
\u6b65\u9aa42\uff1a\u521b\u5efaPython\u865a\u62df\u73af\u5883<\/p>\n
\u5728\u8fdb\u884c\u795e\u7ecf\u7f51\u7edc\u5f00\u53d1\u4e4b\u524d\uff0c\u6211\u4eec\u9700\u8981\u521b\u5efa\u4e00\u4e2aPython\u865a\u62df\u73af\u5883\u3002\u865a\u62df\u73af\u5883\u4f7f\u5f97\u6bcf\u4e2a\u9879\u76ee\u90fd\u6709\u72ec\u7acb\u7684Python\u89e3\u91ca\u5668\u548c\u5e93\uff0c\u907f\u514d\u4e86\u4e0d\u540c\u9879\u76ee\u4e4b\u95f4\u7684\u51b2\u7a81\u3002\u5728\u7ec8\u7aef\u4e2d\u8fd0\u884c\u4ee5\u4e0b\u547d\u4ee4\u521b\u5efa\u5e76\u6fc0\u6d3b\u865a\u62df\u73af\u5883\uff1a<\/p>\n
python3 -m venv myenv\nsource myenv\/bin\/activate<\/pre>\n\u767b\u5f55\u540e\u590d\u5236 <\/p>\n
\u6b65\u9aa43\uff1a\u5b89\u88c5\u6240\u9700\u7684Python\u5e93<\/p>\n
\u795e\u7ecf\u7f51\u7edc\u5f00\u53d1\u901a\u5e38\u9700\u8981\u4f7f\u7528\u4e00\u4e9b\u7b2c\u4e09\u65b9Python\u5e93\uff0c\u5982TensorFlow\u3001Keras\u548cPyTorch\u7b49\u3002\u5728\u6fc0\u6d3b\u7684\u865a\u62df\u73af\u5883\u4e2d\uff0c\u4f7f\u7528pip\u547d\u4ee4\u6765\u5b89\u88c5\u8fd9\u4e9b\u5e93\u3002\u793a\u4f8b\u4ee3\u7801\u5982\u4e0b\uff1a<\/p>\n
pip install tensorflow\npip install keras\npip install torch<\/pre>\n\u767b\u5f55\u540e\u590d\u5236 <\/p>\n
\u6b65\u9aa44\uff1a\u521b\u5efa\u5de5\u7a0b<\/p>\n
\u5728PyCharm\u7684\u754c\u9762\u4e2d\uff0c\u70b9\u51fb”Create New Project”\u6765\u521b\u5efa\u4e00\u4e2a\u65b0\u7684\u5de5\u7a0b\u3002\u9009\u62e9\u4e00\u4e2a\u5408\u9002\u7684\u76ee\u5f55\uff0c\u5e76\u8bbe\u7f6e\u89e3\u91ca\u5668\u4e3a\u865a\u62df\u73af\u5883\u4e2d\u7684Python\u89e3\u91ca\u5668\u3002<\/p>\n
\u6b65\u9aa45\uff1a\u7f16\u5199\u4ee3\u7801<\/p>\n
\u5728\u5de5\u7a0b\u4e2d\u521b\u5efa\u4e00\u4e2aPython\u6587\u4ef6\uff0c\u4f8b\u5982”neural_network.py”\u3002\u5728\u8be5\u6587\u4ef6\u4e2d\uff0c\u6211\u4eec\u5c06\u7f16\u5199\u795e\u7ecf\u7f51\u7edc\u7684\u4ee3\u7801\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u7b80\u5355\u7684\u795e\u7ecf\u7f51\u7edc\u7684\u4ee3\u7801\u793a\u4f8b\uff1a<\/p>\n
import tensorflow as tf\nfrom tensorflow import keras\nimport numpy as np\n\n# \u52a0\u8f7d\u6570\u636e\u96c6\nmnist = keras.datasets.mnist\n(train_images, train_labels), (test_images, test_labels) = mnist.load_data()\n\n# \u5f52\u4e00\u5316\ntrain_images = train_images \/ 255.0\ntest_images = test_images \/ 255.0\n\n# \u6784\u5efa\u6a21\u578b\nmodel = keras.Sequential([\n keras.layers.Flatten(input_shape=(28, 28)),\n keras.layers.Dense(128, activation=tf.nn.relu),\n keras.layers.Dense(10, activation=tf.nn.softmax)\n])\n\n# \u7f16\u8bd1\u6a21\u578b\nmodel.compile(optimizer='adam',\n loss='sparse_categorical_crossentropy',\n metrics=['accuracy'])\n\n# \u8bad\u7ec3\u6a21\u578b\nmodel.fit(train_images, train_labels, epochs=10)\n\n# \u8bc4\u4f30\u6a21\u578b\ntest_loss, test_acc = model.evaluate(test_images, test_labels)\nprint('Test accuracy:', test_acc)<\/pre>\n\u767b\u5f55\u540e\u590d\u5236 <\/p>\n
\u6b65\u9aa46\uff1a\u8fd0\u884c\u4ee3\u7801<\/p>\n
\u5728PyCharm\u7684\u754c\u9762\u4e2d\uff0c\u53f3\u952e\u70b9\u51fb\u4ee3\u7801\u6587\u4ef6\uff0c\u5e76\u9009\u62e9”Run”\u6765\u8fd0\u884c\u4ee3\u7801\u3002PyCharm\u5c06\u4f1a\u8c03\u7528\u865a\u62df\u73af\u5883\u4e2d\u7684Python\u89e3\u91ca\u5668\u6765\u6267\u884c\u4ee3\u7801\u3002\u60a8\u53ef\u4ee5\u5728\u63a7\u5236\u53f0\u4e2d\u67e5\u770b\u4ee3\u7801\u7684\u8f93\u51fa\u7ed3\u679c\u3002<\/p>\n
\u603b\u7ed3\uff1a<\/p>\n
\u672c\u6587\u4ecb\u7ecd\u4e86\u5728linux\u7cfb\u7edf\u4e0a\u4f7f\u7528pycharm\u8fdb\u884c\u795e\u7ecf\u7f51\u7edc\u5f00\u53d1\u7684\u914d\u7f6e\u65b9\u6cd5\u3002\u901a\u8fc7\u6309\u7167\u4ee5\u4e0a\u6b65\u9aa4\u8fdb\u884c\u64cd\u4f5c\uff0c\u60a8\u53ef\u4ee5\u5728PyCharm\u4e2d\u8f7b\u677e\u5f00\u53d1\u548c\u8c03\u8bd5\u795e\u7ecf\u7f51\u7edc\u4ee3\u7801\u3002\u5f53\u7136\uff0c\u8fd9\u53ea\u662f\u4e00\u4e2a\u7b80\u5355\u7684\u793a\u4f8b\uff0c\u60a8\u53ef\u4ee5\u6839\u636e\u81ea\u5df1\u7684\u9700\u6c42\u6765\u7f16\u5199\u66f4\u52a0\u590d\u6742\u7684\u795e\u7ecf\u7f51\u7edc\u4ee3\u7801\u3002\u795d\u60a8\u5728\u795e\u7ecf\u7f51\u7edc\u7814\u7a76\u548c\u5f00\u53d1\u4e2d\u53d6\u5f97\u597d\u6210\u679c\uff01<\/p>\n
\u4ee5\u4e0a\u5c31\u662f\u5728Linux\u7cfb\u7edf\u4e0a\u4f7f\u7528PyCharm\u8fdb\u884c\u795e\u7ecf\u7f51\u7edc\u5f00\u53d1\u7684\u914d\u7f6e\u65b9\u6cd5\u7684\u8be6\u7ec6\u5185\u5bb9\uff0c\u66f4\u591a\u8bf7\u5173\u6ce8FDCServers\u5176\u5b83\u76f8\u5173\u6587\u7ae0\uff01<\/p>\n","protected":false},"excerpt":{"rendered":"
\u5728linux\u7cfb\u7edf\u4e0a\u4f7f\u7528\u8fdb\u884c\u795e\u7ecf\u7f51\u7edc\u5f00\u53d1\u7684\u914d\u7f6e\u65b9\u6cd5 \u968f\u7740\u4eba\u5de5\u667a\u80fd\u548c\u6df1\u5ea6\u5b66\u4e60\u7684\u5feb\u901f\u53d1\u5c55\uff0c\u795e\u7ecf\u7f51\u7edc\u6210\u4e3a\u4e86\u4e00\u4e2a\u70ed\u95e8\u7684\u7814\u7a76\u9886\u57df\u3002PyCharm\u4f5c\u4e3a\u4e00\u6b3e\u5f3a\u5927\u7684Python\u96c6\u6210\u5f00\u53d1\u73af\u5883\uff0c\u53ef\u4ee5\u4e3a\u795e\u7ecf\u7f51\u7edc\u5f00\u53d1\u63d0\u4f9b\u4fbf\u6377\u800c\u9ad8\u6548\u7684\u5de5\u5177\u548c\u529f\u80fd\u3002\u672c\u6587\u5c06\u4ecb\u7ecd\u5728linux\u7cfb\u7edf\u4e0a\u4f7f\u7528pycharm\u8fdb\u884c\u795e\u7ecf\u7f51\u7edc\u5f00\u53d1\u7684\u914d\u7f6e\u65b9\u6cd5\uff0c\u5e76\u63d0\u4f9b\u4ee3\u7801\u793a\u4f8b\u3002 \u6b65\u9aa41\uff1a\u5b89\u88c5PyCharm \u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u4e0b\u8f7d\u548c\u5b89\u88c5PyCharm\u3002\u60a8\u53ef\u4ee5\u5728JetBrains\u7684\u5b98\u65b9\u7f51\u7ad9\u4e0a\u627e\u5230PyCharm\u7684\u6700\u65b0\u7248\u672c\u3002\u9009\u62e9\u9002\u7528\u4e8eLinux\u7cfb\u7edf\u7684\u7248\u672c\uff0c\u5e76\u6309\u7167\u5b98\u65b9\u7684\u5b89\u88c5\u6307\u5357\u8fdb\u884c\u5b89\u88c5\u3002\u5b89\u88c5\u5b8c\u6210\u540e\uff0c\u542f\u52a8PyCharm\u3002 \u6b65\u9aa42\uff1a\u521b\u5efaPython\u865a\u62df\u73af\u5883 \u5728\u8fdb\u884c\u795e\u7ecf\u7f51\u7edc\u5f00\u53d1\u4e4b\u524d\uff0c\u6211\u4eec\u9700\u8981\u521b\u5efa\u4e00\u4e2aPython\u865a\u62df\u73af\u5883\u3002\u865a\u62df\u73af\u5883\u4f7f\u5f97\u6bcf\u4e2a\u9879\u76ee\u90fd\u6709\u72ec\u7acb\u7684Python\u89e3\u91ca\u5668\u548c\u5e93\uff0c\u907f\u514d\u4e86\u4e0d\u540c\u9879\u76ee\u4e4b\u95f4\u7684\u51b2\u7a81\u3002\u5728\u7ec8\u7aef\u4e2d\u8fd0\u884c\u4ee5\u4e0b\u547d\u4ee4\u521b\u5efa\u5e76\u6fc0\u6d3b\u865a\u62df\u73af\u5883\uff1a python3 -m venv myenv source myenv\/bin\/activate \u767b\u5f55\u540e\u590d\u5236 \u6b65\u9aa43\uff1a\u5b89\u88c5\u6240\u9700\u7684Python\u5e93 \u795e\u7ecf\u7f51\u7edc\u5f00\u53d1\u901a\u5e38\u9700\u8981\u4f7f\u7528\u4e00\u4e9b\u7b2c\u4e09\u65b9Python\u5e93\uff0c\u5982TensorFlow\u3001Keras\u548cPyTorch\u7b49\u3002\u5728\u6fc0\u6d3b\u7684\u865a\u62df\u73af\u5883\u4e2d\uff0c\u4f7f\u7528pip\u547d\u4ee4\u6765\u5b89\u88c5\u8fd9\u4e9b\u5e93\u3002\u793a\u4f8b\u4ee3\u7801\u5982\u4e0b\uff1a pip install tensorflow pip install keras pip install torch \u767b\u5f55\u540e\u590d\u5236 \u6b65\u9aa44\uff1a\u521b\u5efa\u5de5\u7a0b \u5728PyCharm\u7684\u754c\u9762\u4e2d\uff0c\u70b9\u51fb”Create New Project”\u6765\u521b\u5efa\u4e00\u4e2a\u65b0\u7684\u5de5\u7a0b\u3002\u9009\u62e9\u4e00\u4e2a\u5408\u9002\u7684\u76ee\u5f55\uff0c\u5e76\u8bbe\u7f6e\u89e3\u91ca\u5668\u4e3a\u865a\u62df\u73af\u5883\u4e2d\u7684Python\u89e3\u91ca\u5668\u3002 \u6b65\u9aa45\uff1a\u7f16\u5199\u4ee3\u7801 \u5728\u5de5\u7a0b\u4e2d\u521b\u5efa\u4e00\u4e2aPython\u6587\u4ef6\uff0c\u4f8b\u5982”neural_network.py”\u3002\u5728\u8be5\u6587\u4ef6\u4e2d\uff0c\u6211\u4eec\u5c06\u7f16\u5199\u795e\u7ecf\u7f51\u7edc\u7684\u4ee3\u7801\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u7b80\u5355\u7684\u795e\u7ecf\u7f51\u7edc\u7684\u4ee3\u7801\u793a\u4f8b\uff1a import tensorflow as tf from tensorflow import keras import numpy as np # \u52a0\u8f7d\u6570\u636e\u96c6 mnist = keras.datasets.mnist (train_images, train_labels), (test_images, test_labels) = mnist.load_data() # […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[8],"tags":[],"class_list":["post-61273","post","type-post","status-publish","format-standard","hentry","category-os"],"_links":{"self":[{"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/posts\/61273","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/comments?post=61273"}],"version-history":[{"count":0,"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/posts\/61273\/revisions"}],"wp:attachment":[{"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/media?parent=61273"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/categories?post=61273"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/fwq.ai\/blog\/wp-json\/wp\/v2\/tags?post=61273"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}