{"id":19,"date":"2019-01-10T19:14:02","date_gmt":"2019-01-10T15:44:02","guid":{"rendered":"http:\/\/themes.tielabs.com\/sahifa5\/?p=19"},"modified":"2019-05-03T08:38:07","modified_gmt":"2019-05-03T04:08:07","slug":"tensorflow-intro","status":"publish","type":"post","link":"https:\/\/shahaab-co.com\/mag\/edu\/tensorflow-intro\/","title":{"rendered":"\u0622\u0634\u0646\u0627\u06cc\u06cc \u0628\u0627 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u062a\u0646\u0633\u0648\u0631\u0641\u0644\u0648"},"content":{"rendered":"
\n

\u062a\u0646\u0633\u0648\u0631\u0641\u0644\u0648\u060c \u06cc\u06a9 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u06cc \u0645\u062a\u0646 \u0628\u0627\u0632 \u06cc\u0627\u062f\u06af\u06cc\u0631\u06cc \u0639\u0645\u06cc\u0642<\/a> \u0628\u0631\u0627\u06cc \u0632\u0628\u0627\u0646 \u067e\u0627\u06cc\u062a\u0648\u0646 ( \u0648 \u0632\u0628\u0627\u0646 ++C) \u0627\u0633\u062a \u06a9\u0647 \u062a\u0648\u0633\u0637 \u062a\u06cc\u0645 Google Brain \u062f\u0631 \u0646\u0647\u0645 \u0646\u0648\u0627\u0645\u0628\u0631 \u06f2\u06f0\u06f1\u06f5 \u0645\u0639\u0631\u0641\u06cc \u0634\u062f. \u0627\u0645\u0631\u0648\u0632\u0647 \u06af\u0648\u06af\u0644 \u0627\u0632 \u0627\u06cc\u0646 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u0628\u0631\u0627\u06cc \u0645\u0648\u0627\u0631\u062f\u06cc \u0686\u0648\u0646 \u0628\u0627\u0632\u0634\u0646\u0627\u0633\u06cc \u06af\u0641\u062a\u0627\u0631\u060c Gmail\u060c Google photo \u0648 \u0633\u0631\u0648\u06cc\u0633 \u0647\u0627\u06cc \u062c\u0633\u062a \u0648\u062c\u0648 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0645\u06cc \u06a9\u0646\u062f.\u0627\u0632 \u0622\u0646\u062c\u0627\u06cc\u06cc \u06a9\u0647 \u062a\u0646\u0633\u0648\u0631 \u0641\u0644\u0648 \u0628\u0631 \u0627\u0633\u0627\u0633 \u0631\u0648\u0634 \u0647\u0627\u06cc \u0645\u0628\u062a\u0646\u06cc \u0628\u0631 \u06cc\u0627\u062f\u06af\u06cc\u0631\u06cc \u0639\u0645\u06cc\u0642 \u0637\u0631\u0627\u062d\u06cc \u0634\u062f\u0647 \u0627\u0633\u062a\u060c \u0642\u0627\u0628\u0644\u06cc\u062a \u0627\u062c\u0631\u0627\u06cc \u0641\u0639\u0627\u0644\u06cc\u062a\u0647\u0627\u06cc \u067e\u0631\u062f\u0627\u0632\u0634\u06cc \u0633\u0646\u06af\u06cc\u0646 \u0645\u062b\u0644 \u0631\u0648\u0634 \u0647\u0627\u06cc \u062e\u0648\u0634\u0647 \u0628\u0646\u062f\u06cc\u060c \u0645\u062f\u0644 \u0647\u0627\u06cc \u06af\u0631\u0627\u0641\u06cc\u06a9\u06cc\u060c \u0645\u0633\u0627\u0626\u0644 \u0628\u0647\u06cc\u0646\u0647 \u0633\u0627\u0632\u06cc \u0648 …\u0631\u0627 \u062f\u0627\u0631\u0627 \u0645\u06cc \u0628\u0627\u0634\u062f. \u0627\u0632 \u0648\u06cc\u0698\u06af\u06cc \u0647\u0627\u06cc \u0627\u06cc\u0646 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u0645\u06cc \u062a\u0648\u0627\u0646 \u0628\u0647 \u0645\u0634\u062a\u0642 \u06af\u06cc\u0631\u06cc \u0627\u062a\u0648\u0645\u0627\u062a\u06cc\u06a9( \u06a9\u0647 \u0646\u06cc\u0627\u0632 \u0628\u0647 \u0646\u0648\u0634\u062a\u0646 \u06a9\u062f\u0647\u0627\u06cc \u062f\u0633\u062a\u06cc \u0628\u0631\u0627\u06cc \u067e\u06cc\u0627\u062f\u0647 \u0633\u0627\u0632\u06cc \u0627\u0644\u06af\u0648\u0631\u06cc\u062a\u0645 \u067e\u0633 \u0627\u0646\u062a\u0634\u0627\u0631 \u0631\u0627 \u0631\u0641\u0639 \u0645\u06cc \u06a9\u0646\u062f)\u060c \u062e\u0627\u0635\u06cc\u062a \u0645\u0648\u0627\u0632\u06cc \u0633\u0627\u0632\u06cc \u0627\u062a\u0648\u0645\u0627\u062a\u06cc\u06a9 \u0648 \u0628\u06a9\u0627\u0631 \u06af\u06cc\u0631\u06cc GPU \u062f\u0631 \u067e\u0631\u062f\u0627\u0632\u0634 \u0647\u0627\u06cc \u0633\u0646\u06af\u06cc\u0646 \u0627\u0634\u0627\u0631\u0647 \u06a9\u0631\u062f.\u06cc\u06a9\u06cc \u0627\u0632 \u0642\u0627\u0628\u0644\u06cc\u062a \u0647\u0627\u06cc \u062e\u0648\u0628 \u062a\u0646\u0633\u0648\u0631\u0641\u0644\u0648\u060c \u0627\u0628\u0632\u0627\u0631 TensorBoard \u0627\u0633\u062a. \u062a\u0646\u0633\u0648\u0631\u0628\u0631\u062f<\/a> \u0627\u0628\u0632\u0627\u0631\u06cc \u0627\u0633\u062a \u06a9\u0647 \u0628\u0647 \u0628\u0631\u0646\u0627\u0645\u0647 \u0646\u0648\u06cc\u0633\u060c \u0627\u062c\u0627\u0632\u0647 \u06cc \u0645\u0635\u0648\u0631\u0633\u0627\u0632\u06cc \u06af\u0631\u0627\u0641 \u0645\u062d\u0627\u0633\u0628\u0627\u062a\u06cc \u0631\u0627 \u0645\u06cc \u062f\u0647\u062f. \u06af\u0631\u0627\u0641\u06cc \u06a9\u0647 \u0645\u0628\u06cc\u0646 \u0645\u0633\u06cc\u0631 \u0648 \u0686\u0627\u0631\u0686\u0648\u0628 \u06a9\u0644\u06cc \u0645\u062d\u0627\u0633\u0628\u0627\u062a\u06cc \u0648 \u0631\u0641\u062a\u0627\u0631\u06cc \u0645\u0633\u0626\u0644\u0647 \u06cc \u0645\u0648\u0631\u062f \u0628\u0631\u0631\u0633\u06cc \u0627\u0633\u062a.\u062a\u0646\u0633\u0648\u0631 \u0641\u0644\u0648 \u0628\u0627 \u062a\u0639\u0631\u06cc\u0641 \u06a9\u0631\u062f\u0646 \u06cc\u06a9 \u06af\u0631\u0627\u0641 \u0639\u0645\u0644\u06cc\u0627\u062a\u06cc \u062f\u0627\u062f\u0647 \u0627\u06cc \u06a9\u0627\u0631 \u0645\u06cc \u06a9\u0646\u062f.\u06af\u0631\u0627\u0641\u06cc \u06a9\u0647 \u0636\u0644\u0639 \u0647\u0627\u06cc \u0622\u0646\u060c \u0645\u0639\u0631\u0641 \u062f\u0627\u062f\u0647 \u0647\u0627 \u0648 \u06af\u0631\u0647 \u0647\u0627\u06cc \u0622\u0646 \u0645\u0639\u0631\u0641 \u0639\u0645\u0644\u06cc\u0627\u062a \u0647\u0627 \u0627\u0633\u062a. \u062f\u0631 \u062a\u0646\u0633\u0648\u0631 \u0641\u0644\u0648\u060c \u0628\u0631\u0646\u0627\u0645\u0647 \u0646\u0648\u06cc\u0633\u060c \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u062a\u0646\u0633\u0648\u0631\u0647\u0627 \u06cc\u06a9 \u06af\u0631\u0627\u0641 \u0645\u062d\u0627\u0633\u0628\u0627\u062a\u06cc \u0631\u0627 \u062a\u0639\u0631\u06cc\u0641 \u0645\u06cc \u06a9\u0646\u062f.<\/p>\n

\"\u062a\u0646\u0633\u0648\u0631\u0641\u0644\u0648<\/a><\/p>\n

\u0646\u0635\u0628 \u0648 \u0631\u0627\u0647 \u0627\u0646\u062f\u0627\u0632\u06cc<\/strong><\/p>\n

\u0628\u0631\u0627\u06cc \u0646\u0635\u0628 \u0627\u06cc\u0646 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647\u060c \u06cc\u06a9 \u0631\u0627\u0647\u0646\u0645\u0627\u06cc \u0622\u0645\u0648\u0632\u0634\u06cc \u06a9\u0647 \u0628\u0637\u0648\u0631 \u067e\u06cc\u0648\u0633\u062a\u0647 \u0648 \u0645\u062f\u0627\u0648\u0645 \u0628\u0631\u0648\u0632 \u0631\u0633\u0627\u0646\u06cc \u0645\u06cc \u0634\u0648\u062f\u060c \u062f\u0631 \u0622\u062f\u0631\u0633 \u0632\u06cc\u0631 \u0648\u062c\u0648\u062f \u062f\u0627\u0631\u062f:<\/p>\n

https:\/\/www.tensorflow.org\/get_started<\/a><\/p>\n

\u062f\u0631 \u0627\u062f\u0627\u0645\u0647 \u06cc\u06a9 \u0645\u062b\u0627\u0644 \u0627\u0632 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u06cc \u062a\u0646\u0633\u0648\u0631 \u0641\u0644\u0648 \u0627\u0631\u0627\u0626\u0647 \u0634\u062f\u0647 \u0627\u0633\u062a.<\/p>\n

\u0631\u06af\u0631\u06cc\u0633\u06cc\u0648\u0646 \u062e\u0637\u06cc \u062f\u0631 \u062a\u0646\u0633\u0648\u0631 \u0641\u0644\u0648<\/strong><\/p>\n

\u0631\u06af\u0631\u06cc\u0633\u06cc\u0648\u0646 \u062e\u0637\u06cc \u062f\u0631 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u06cc \u062a\u0646\u0633\u0648\u0631\u0641\u0644\u0648 \u0628\u0647 \u0634\u06a9\u0644\u06cc \u06a9\u0647 \u062f\u0631 \u0627\u062f\u0627\u0645\u0647 \u0628\u06cc\u0627\u0646 \u062e\u0648\u0627\u0647\u06cc\u0645 \u06a9\u0631\u062f \u062a\u0639\u0631\u06cc\u0641 \u0645\u06cc \u0634\u0648\u062f:<\/p>\n

\u062f\u0631 \u0627\u0628\u062a\u062f\u0627 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u0647\u0627\u06cc \u0644\u0627\u0632\u0645 \u0628\u0631\u0627\u06cc \u0627\u062c\u0631\u0627 \u0631\u0627 \u0641\u0631\u0627\u062e\u0648\u0627\u0646\u06cc \u0645\u06cc\u06a9\u0646\u06cc\u0645 \u0648 \u0633\u067e\u0633 \u062f\u0627\u062f\u0647 \u0647\u0627\u06cc \u0645\u0648\u0631\u062f \u0646\u0638\u0631 \u0631\u0627 \u0641\u0631\u0627\u062e\u0648\u0627\u0646\u06cc \u0648 \u0628\u0647 \u062f\u0648 \u062f\u0633\u062a\u0647 \u06cc \u062f\u0627\u062f\u0647 \u0647\u0627\u06cc \u0622\u0645\u0648\u0632\u0634 \u0648 \u062f\u0627\u062f\u0647\u0627\u06cc \u062a\u0633\u062a \u062a\u0642\u0633\u06cc\u0645 \u0645\u06cc \u06a9\u0646\u06cc\u0645:<\/p>\n

import numpy as np\nimport matplotlib.pyplot as plt\nimport tensorflow as tf\n# NEW DATA\ndata_x = np.linspace(1, 8, 100)[:, np.newaxis]\ndata_y = np.polyval([1, -14, 59, -70], data_x) \n        + \u06f1\u066b\u06f5 * np.sin(data_x) + np.random.randn(100, 1)\n# --------\nmodel_order = 5\ndata_x = np.power(data_x, range(model_order))\ndata_x \/= np.max(data_x, axis=0)\norder = np.random.permutation(len(data_x))\nportion = 20\ntest_x = data_x[order[:portion]]\ntest_y = data_y[order[:portion]]\ntrain_x = data_x[order[portion:]]\ntrain_y = data_y[order[portion:]]\n<\/code><\/pre>\n
\u062f\u0631 \u0627\u062f\u0627\u0645\u0647 \u0628\u0627\u06cc\u062f \u0645\u062f\u0644 \u062e\u0648\u062f \u0631\u0627 \u06cc\u0627 \u0647\u0645\u0627\u0646 \u06af\u0631\u0627\u0641 \u0645\u0633\u0626\u0644\u0647 \u0631\u0627 \u062a\u0639\u0631\u06cc\u0641 \u06a9\u0646\u06cc\u0645. \u0628\u0631\u0627\u06cc \u0627\u06cc\u0646 \u06a9\u0627\u0631 \u0627\u0628\u062a\u062f\u0627 \u0646\u06af\u0647\u062f\u0627\u0631\u0646\u062f\u0647 \u0647\u0627\u06cc \u0648\u0631\u0648\u062f\u06cc \u0647\u0627 \u0648 \u062e\u0631\u0648\u062c\u06cc \u0647\u0627\u06cc\u0645\u0627\u0646 \u0631\u0627 \u062a\u0639\u0631\u06cc\u0641 \u0645\u06cc \u06a9\u0646\u06cc\u0645 \u06a9\u0647 \u0628\u0631\u0627\u06cc \u067e\u06cc\u0627\u062f\u0647 \u0633\u0627\u0632\u06cc \u0622\u0646 \u0628\u0627\u06cc\u062f \u0646\u0648\u0639 \u062f\u0627\u062f\u0647 \u0647\u0627(float32)\u060c \u0634\u06a9\u0644 \u062f\u0627\u062f\u0647 \u0647\u0627 \u0631\u0627 \u0628\u0647 \u0635\u0648\u0631\u062a \u0632\u06cc\u0631 \u062a\u0639\u0631\u06cc\u0641 \u06a9\u0646\u06cc\u0645:<\/p>\n
with tf.name_scope(\"IO\"):\n    inputs = tf.placeholder(tf.float32, [None, model_order], name=\"X\")\n    outputs = tf.placeholder(tf.float32, [None, 1], name=\"Yhat\")\n<\/code><\/pre>\n
\u062f\u0631 \u0627\u062f\u0627\u0645\u0647 \u0645\u062f\u0644 \u0631\u06af\u0631\u06cc\u0633\u06cc\u0648\u0646 \u062e\u0637\u06cc \u0631\u0627 \u062a\u0639\u0631\u06cc\u0641 \u0645\u06cc \u06a9\u0646\u06cc\u0645:<\/p>\n
with tf.name_scope(\"LR\"):\n    W = tf.Variable(tf.zeros([model_order, 1], dtype=tf.float32), name=\"W\")\n    y = tf.matmul(inputs, W)\n<\/code><\/pre>\n
\u0648 \u062f\u0631 \u0646\u0647\u0627\u06cc\u062a \u062a\u0627\u0628\u0639 \u0647\u0632\u06cc\u0646\u0647 \u0648 \u0628\u0647\u06cc\u0646\u0647 \u0633\u0627\u0632 \u062e\u0648\u062f \u0631\u0627 \u062a\u0639\u0631\u06cc\u0641 \u0645\u06cc \u0646\u0645\u0627\u06cc\u06cc\u0645:<\/p>\n
with tf.name_scope(\"train\"):\n    learning_rate = tf.Variable(0.5, trainable=False)\n    cost_op = tf.reduce_mean(tf.pow(y-outputs, 2))\n    train_op = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost_op)\n<\/code><\/pre>\n
\u0647\u0645\u0627\u0646\u0637\u0648\u0631 \u06a9\u0647 \u062f\u0631 \u0628\u0627\u0644\u0627 \u0645\u0634\u0627\u0647\u062f\u0647 \u0646\u0645\u0648\u062f\u06cc\u062f\u060c \u0646\u06cc\u0627\u0632\u06cc \u0628\u0647 \u062a\u0639\u0631\u06cc\u0641 \u06af\u0631\u0627\u062f\u06cc\u0627\u0646 \u06cc\u0627 \u0628\u0631\u0648\u0632\u0631\u0633\u0627\u0646\u06cc \u0645\u062f\u0627\u0648\u0645 \u067e\u0627\u0631\u0627\u0645\u062a\u0631\u0647\u0627 \u0646\u0628\u0648\u062f. \u062d\u0627\u0644 \u0628\u0647 \u067e\u06cc\u0627\u062f\u0647 \u0633\u0627\u0632\u06cc \u0627\u062c\u0631\u0627\u06cc\u06cc \u0645\u062f\u0644 \u062e\u0648\u062f\u0645\u0627\u0646 \u062f\u0631 GPU \u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 \u062f\u0627\u062f\u0647 \u0647\u0627\u06cc \u0622\u0645\u0648\u0632\u0634 \u0645\u06cc \u067e\u0631\u062f\u0627\u0632\u06cc\u0645 \u0648 \u0628\u0647 \u0635\u0648\u0631\u062a \u0632\u06cc\u0631 \u0639\u0645\u0644 \u0645\u06cc \u06a9\u0646\u06cc\u0645:<\/p>\n
tolerance = 1e-3\n# Perform Stochastic Gradient Descent\nepochs = 1\nlast_cost = 0\nalpha = 0.4\nmax_epochs = 50000\nsess = tf.Session() # Create TensorFlow session\nprint \"Beginning Training\"\nwith sess.as_default():\n    init = tf.initialize_all_variables()\n    sess.run(init)\n    sess.run(tf.assign(learning_rate, alpha))\n    while True:\n        # Execute Gradient Descent\n        sess.run(train_op, feed_dict={inputs: train_x, outputs: train_y})\n        # Keep track of our performance\n        if epochs%100==0:\n            cost = sess.run(cost_op, feed_dict={inputs: train_x, outputs: train_y})\n            print \"Epoch: %d - Error: %.4f\" %(epochs, cost)\n            # Stopping Condition\n            if abs(last_cost - cost) < tolerance or epochs > max_epochs:\n                print \"Converged.\"\n                break\n            last_cost = cost\n        epochs += 1\n    w = W.eval()\n    print \"w =\", w\n    print \"Test Cost =\", sess.run(cost_op, feed_dict={inputs: test_x, outputs: test_y})\n<\/code><\/pre>\n
\u0646\u062a\u06cc\u062c\u0647 \u06cc \u0627\u0639\u0645\u0627\u0644 \u062f\u0627\u062f\u0647 \u0647\u0627\u06cc \u0622\u0645\u0648\u0632\u0634 \u0628\u0647 \u0634\u0628\u06a9\u0647 \u0628\u0647 \u0635\u0648\u0631\u062a \u0632\u06cc\u0631 \u0627\u0633\u062a:<\/p>\n
\"\u0631\u06af\u0631\u0633\u06cc\u0648\u0646<\/a><\/p>\n<\/div>\n
\n
\u0628\u0627 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0627\u0632 TensorBoard \u0645\u062f\u0644 \u0645\u0627 \u0628\u0647 \u0635\u0648\u0631\u062a \u0632\u06cc\u0631 \u0627\u0633\u062a:<\/p>\n
\"\u06af\u0631\u0627\u0641<\/a><\/p>\n
\u0645\u0646\u0628\u0639:<\/p>\n
https:\/\/www.cs.toronto.edu\/~frossard\/post\/tensorflow\/<\/p>\n<\/div>\n\n\n
\n            \n
\n    \n
\n            
\n            \n\n
<\/div>\n        <\/div>\n            
\n            \n\n
<\/div>\n        <\/div>\n            
\n            \n\n
<\/div>\n        <\/div>\n            
\n            \n\n
<\/div>\n        <\/div>\n            
\n            \n\n
<\/div>\n        <\/div>\n    <\/div>\n    \n
\n            
\n            \n\n
<\/div>\n        <\/div>\n            
\n            \n\n
<\/div>\n        <\/div>\n            
\n            \n\n
<\/div>\n        <\/div>\n            
\n            \n\n
<\/div>\n        <\/div>\n            
\n            \n\n
<\/div>\n        <\/div>\n    <\/div>\n<\/div>\n                \n\n
\n            \u0627\u0645\u062a\u06cc\u0627\u0632 \u062f\u0647\u06cc\u062f!<\/span>\n    <\/div>\n    <\/div>\n","protected":false},"excerpt":{"rendered":"
\u062a\u0646\u0633\u0648\u0631\u0641\u0644\u0648\u060c \u06cc\u06a9 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u06cc \u0645\u062a\u0646 \u0628\u0627\u0632 \u06cc\u0627\u062f\u06af\u06cc\u0631\u06cc \u0639\u0645\u06cc\u0642 \u0628\u0631\u0627\u06cc \u0632\u0628\u0627\u0646 \u067e\u0627\u06cc\u062a\u0648\u0646 ( \u0648 \u0632\u0628\u0627\u0646 ++C) \u0627\u0633\u062a \u06a9\u0647 \u062a\u0648\u0633\u0637 \u062a\u06cc\u0645 Google Brain \u062f\u0631 \u0646\u0647\u0645 \u0646\u0648\u0627\u0645\u0628\u0631 \u06f2\u06f0\u06f1\u06f5 \u0645\u0639\u0631\u0641\u06cc \u0634\u062f. \u0627\u0645\u0631\u0648\u0632\u0647 \u06af\u0648\u06af\u0644 \u0627\u0632 \u0627\u06cc\u0646 \u06a9\u062a\u0627\u0628\u062e\u0627\u0646\u0647 \u0628\u0631\u0627\u06cc \u0645\u0648\u0627\u0631\u062f\u06cc \u0686\u0648\u0646 \u0628\u0627\u0632\u0634\u0646\u0627\u0633\u06cc \u06af\u0641\u062a\u0627\u0631\u060c Gmail\u060c Google photo \u0648 \u0633\u0631\u0648\u06cc\u0633 \u0647\u0627\u06cc \u062c\u0633\u062a \u0648\u062c\u0648 \u0627\u0633\u062a\u0641\u0627\u062f\u0647 \u0645\u06cc \u06a9\u0646\u062f.\u0627\u0632 \u0622\u0646\u062c\u0627\u06cc\u06cc \u06a9\u0647 \u062a\u0646\u0633\u0648\u0631 \u0641\u0644\u0648 \u0628\u0631 \u0627\u0633\u0627\u0633 \u0631\u0648\u0634 …<\/p>\n","protected":false},"author":8,"featured_media":1243,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_editorskit_title_hidden":false,"_editorskit_reading_time":0,"_editorskit_is_block_options_detached":false,"_editorskit_block_options_position":"{}","footnotes":""},"categories":[18,19],"tags":[84,82,86],"class_list":["post-19","post","type-post","status-publish","format-standard","has-post-thumbnail","","category-edu","category-deep-learning","tag-84","tag-82","tag-86"],"_links":{"self":[{"href":"https:\/\/shahaab-co.com\/mag\/wp-json\/wp\/v2\/posts\/19","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/shahaab-co.com\/mag\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/shahaab-co.com\/mag\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/shahaab-co.com\/mag\/wp-json\/wp\/v2\/users\/8"}],"replies":[{"embeddable":true,"href":"https:\/\/shahaab-co.com\/mag\/wp-json\/wp\/v2\/comments?post=19"}],"version-history":[{"count":0,"href":"https:\/\/shahaab-co.com\/mag\/wp-json\/wp\/v2\/posts\/19\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/shahaab-co.com\/mag\/wp-json\/wp\/v2\/media\/1243"}],"wp:attachment":[{"href":"https:\/\/shahaab-co.com\/mag\/wp-json\/wp\/v2\/media?parent=19"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/shahaab-co.com\/mag\/wp-json\/wp\/v2\/categories?post=19"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/shahaab-co.com\/mag\/wp-json\/wp\/v2\/tags?post=19"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}