{ "cells": [ { "cell_type": "markdown", "id": "2111825f", "metadata": { "id": "2111825f" }, "source": [ "

نام طرح

" ] }, { "cell_type": "markdown", "id": "1ab61eab", "metadata": { "id": "1ab61eab" }, "source": [ "

فراخوانی کتابخانه های مورد نیاز

" ] }, { "cell_type": "code", "execution_count": 2, "id": "b97c8a8b", "metadata": { "id": "b97c8a8b" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "2024-11-25 22:06:12.893677: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n", "To enable the following instructions: SSE4.1 SSE4.2 AVX AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n" ] } ], "source": [ "import numpy as np\n", "import matplotlib.pyplot as plt\n", "import tensorflow as tf\n", "from tensorflow import keras\n", "from tensorflow.keras.layers import Dense, Input, Flatten, Conv2D, SimpleRNN, LSTM\n", "from tensorflow.keras.models import Model\n", "from tensorflow.keras.datasets import mnist" ] }, { "cell_type": "markdown", "id": "79ef7ea0", "metadata": { "id": "79ef7ea0" }, "source": [ "

لود کردن دیتاست MNIST

" ] }, { "cell_type": "code", "execution_count": 3, "id": "511bc7e3", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "511bc7e3", "outputId": "af449f04-1da5-4b14-89af-75adf6100681" }, "outputs": [], "source": [ "train_set, test_set = mnist.load_data()" ] }, { "cell_type": "markdown", "id": "8af0ed71", "metadata": { "id": "8af0ed71" }, "source": [ "

طراحی لایه های استخراج ویژگی و سنجش نسبت ها

" ] }, { "cell_type": "markdown", "id": "bb994741", "metadata": { "id": "bb994741" }, "source": [ "

لایه استخراج ویژگی

" ] }, { "cell_type": "code", "execution_count": 4, "id": "8494ca6d", "metadata": { "id": "8494ca6d" }, "outputs": [], "source": [ "# لایه استخراج ویژگی\n", "kernel_initializer = 'normal'\n", "activation = \"relu\"\n", "\n", "dtype = tf.float32\n", "\n", "\n", "def get_module_1():\n", " shape=(28,28, 1)\n", " chs=1\n", " inputs = Input(shape)\n", " layer = Conv2D(filters=32*chs, kernel_size=(3,3), activation=activation, kernel_initializer=kernel_initializer)(inputs)\n", " layer = Conv2D(filters=16*chs, kernel_size=(3,3), strides=(2, 2), activation=activation, kernel_initializer=kernel_initializer)(layer)\n", " layer = Conv2D(filters=8*chs, kernel_size=(3,3), activation=activation, kernel_initializer=kernel_initializer)(layer)\n", " layer = Conv2D(filters=4*chs, kernel_size=(3,3), strides=(2, 2), activation='linear', kernel_initializer=kernel_initializer)(layer)\n", " layer = Conv2D(filters=64*2, kernel_size=(4,4), activation='softplus', kernel_initializer=kernel_initializer)(layer)\n", " layer = Flatten()(layer)\n", " model = Model(inputs, layer)\n", "\n", " return model" ] }, { "cell_type": "markdown", "id": "ed717db9", "metadata": { "id": "ed717db9" }, "source": [ "

لایه سنجش نسبت ها

" ] }, { "cell_type": "code", "execution_count": 5, "id": "f63a27eb", "metadata": { "id": "f63a27eb" }, "outputs": [], "source": [ "# لایه سنجش نسبت ها\n", "def get_module_2():\n", " shape=(1, 64*2+10,)\n", " inputs = Input(shape)\n", " lstm1 = LSTM(64, return_sequences=True)(inputs)\n", " lstm2 = LSTM(32)(lstm1)\n", " outputs = Dense(10, activation='softmax')(lstm2)\n", " model = Model(inputs, outputs)\n", " return model" ] }, { "cell_type": "code", "execution_count": 8, "id": "a2848909", "metadata": {}, "outputs": [], "source": [ "def get_module_3():\n", " shape=(1, 10,)\n", " inputs = Input(shape)\n", " lstm1 = LSTM(64, return_sequences=True)(inputs)\n", " lstm2 = LSTM(32)(lstm1)\n", " outputs = Dense(10, activation='softmax')(lstm2)\n", " model = Model(inputs, outputs)\n", " return model" ] }, { "cell_type": "markdown", "id": "614adfad", "metadata": { "id": "614adfad" }, "source": [ "

طراحی‌ و ساختن شبکه عصبی

" ] }, { "cell_type": "code", "execution_count": 9, "id": "6a14ab0a", "metadata": { "id": "6a14ab0a" }, "outputs": [], "source": [ "def get_m2_input_vector(f0, f1, lbl1):\n", " # ترکیب ویژگی های کلاس مورد مطالعه با کلاس های دیگر\n", "\n", " inp = f0 * f1\n", " return tf.concat([inp, lbl1], axis=1)\n", "\n", "\n", "class InfluenceModel(keras.Model):\n", " def __init__(self, module_1, module_2):\n", " super(InfluenceModel, self).__init__()\n", " # لایه استخراج ویژگی\n", " self.module_1 = module_1\n", " # لایه تمام متصل (سنجش نسبت ها)\n", " self.module_2 = module_2\n", "\n", " self.loss = keras.losses.SparseCategoricalCrossentropy(from_logits=False)\n", " self.metric = keras.metrics.SparseCategoricalAccuracy()\n", "\n", "\n", " def compile(self, optimizer_1, optimizer_2):\n", " super(InfluenceModel, self).compile()\n", " self.optimizer_1 = optimizer_1\n", " self.optimizer_2 = optimizer_2\n", "\n", " def call_at_zero(self, x):\n", " # جدا کردن تصاویر\n", " imgs = x[0]\n", " # جدا کردن برچسب\n", " lbls = tf.one_hot(x[1], 10)\n", "\n", " # استخراج ویژگی های تصاویر\n", " features = self.module_1(imgs)\n", "\n", " n_feat = features.shape[0]\n", " # جدا سازی ویژگی های هر تصویر\n", " features = tf.split(features, n_feat, axis=0)\n", "\n", " # ویژگی های استحراج شده تصویر مورد مطالعه\n", " f0 = features[0]\n", "\n", " res_mtx = []\n", " res_row = []\n", " for j in range(1, n_feat):\n", " # ترکیب هر نمونه با تصویر مورد مطالعه\n", " f1 = features[j]\n", " lbl1 = lbls[j:j+1,:]\n", " inp = get_m2_input_vector(f0, f1, lbl1)\n", "\n", " res_row += [inp]\n", "\n", " # محاسبه نسبت هر نمونه با تصویر مورد مطالعه\n", " res_row = tf.concat(res_row, axis=0)\n", " res_row = tf.expand_dims(res_row, axis=1)\n", " res_mtx = self.module_2(res_row)\n", "\n", " # میانگین بر روی نمونه ها\n", " res = tf.reduce_sum(res_mtx, axis=0) / (n_feat-1)\n", " return res, res_mtx\n", "\n", " # Feed - Forward\n", " def call(self, x):\n", " # جدا کردن تصاویر\n", " imgs = x[0]\n", " # جدا کردن برچسب\n", " lbls = tf.one_hot(x[1], 10)\n", "\n", " # استخراج ویژگی های تصاویر\n", " features = self.module_1(imgs)\n", "\n", " # جدا سازی ویژگی های هر تصویر\n", " n_feat = features.shape[0]\n", " features = tf.split(features, n_feat, axis=0)\n", "\n", "\n", " res_mtx = []\n", " # ساخت جفت های ترکیب شده به ازای هر تصویر برای اموزش مدل\n", " for i in range(n_feat):\n", " res_row = []\n", " for j in range(n_feat):\n", " f0 = features[i]\n", " f1 = features[j]\n", " lbl1 = lbls[j:j+1,:]\n", " inp = get_m2_input_vector(f0, f1, lbl1)\n", " res_row += [inp]\n", " res_row = tf.concat(res_row, axis=0)\n", " res_row = tf.cast(res_row, dtype=tf.float32)\n", " res_row = tf.expand_dims(res_row, axis=1)\n", " # محاسبه سنجش تاثیر حضور تصاویر دیگر در پیش بینی تصویر مورد مطالعه\n", " res_mtx += [self.module_2(res_row)]\n", "\n", " res_mtx = tf.stack(res_mtx)\n", " #\n", " res_mtx = tf.transpose(res_mtx, [2, 1, 0])\n", " #\n", " res_mtx -= tf.linalg.diag(tf.linalg.diag_part(res_mtx))\n", " #\n", " res_mtx = tf.transpose(res_mtx, [2, 1, 0])\n", " #\n", " print(res_mtx.shape)\n", " res = tf.reduce_sum(res_mtx, axis=1) / (n_feat-1)\n", "\n", " return res, res_mtx\n", "\n", " def train_step(self, x):\n", " # تعریف تابع ضرر\n", " loss = keras.losses.SparseCategoricalCrossentropy(from_logits=False)\n", "\n", " # محاسبه گرادیان و اعمال گرادیان\n", " with tf.GradientTape() as tape_1, tf.GradientTape() as tape_2:\n", " output, _ = self.call(x)\n", " loss_batch = loss(x[1], output)\n", " gradient_1 = tape_1.gradient(loss_batch, self.module_1.trainable_variables)\n", " self.optimizer_1.apply_gradients(zip(gradient_1, self.module_1.trainable_variables))\n", " gradient_2 = tape_2.gradient(loss_batch, self.module_2.trainable_variables)\n", " self.optimizer_2.apply_gradients(zip(gradient_2, self.module_2.trainable_variables))\n", "\n", " # اعمال معیار ارزیابی\n", " metric_batch = self.metric(x[1], output)\n", "\n", " return {\"loss\": loss_batch, \"metric\": metric_batch}\n" ] }, { "cell_type": "markdown", "id": "c1a0891a", "metadata": { "id": "c1a0891a" }, "source": [ "

اموزش مدل

" ] }, { "cell_type": "markdown", "id": "67d4458d", "metadata": { "id": "67d4458d" }, "source": [ "

اتصال لایه ها

" ] }, { "cell_type": "code", "execution_count": 10, "id": "f6ed77af", "metadata": { "id": "f6ed77af" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "2024-11-25 22:07:38.582469: I tensorflow/core/common_runtime/process_util.cc:146] Creating new thread pool with default inter op setting: 2. Tune using inter_op_parallelism_threads for best performance.\n", "2024-11-25 22:07:39.158327: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'gradients/split_2_grad/concat/split_2/split_dim' with dtype int32\n", "\t [[{{node gradients/split_2_grad/concat/split_2/split_dim}}]]\n", "2024-11-25 22:07:39.160707: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'gradients/split_grad/concat/split/split_dim' with dtype int32\n", "\t [[{{node gradients/split_grad/concat/split/split_dim}}]]\n", "2024-11-25 22:07:39.162665: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'gradients/split_1_grad/concat/split_1/split_dim' with dtype int32\n", "\t [[{{node gradients/split_1_grad/concat/split_1/split_dim}}]]\n", "2024-11-25 22:07:39.421363: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'gradients/split_2_grad/concat/split_2/split_dim' with dtype int32\n", "\t [[{{node gradients/split_2_grad/concat/split_2/split_dim}}]]\n", "2024-11-25 22:07:39.424466: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'gradients/split_grad/concat/split/split_dim' with dtype int32\n", "\t [[{{node gradients/split_grad/concat/split/split_dim}}]]\n", "2024-11-25 22:07:39.426262: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'gradients/split_1_grad/concat/split_1/split_dim' with dtype int32\n", "\t [[{{node gradients/split_1_grad/concat/split_1/split_dim}}]]\n" ] } ], "source": [ "m1 = get_module_1()\n", "m2 = get_module_2()\n", "\n", "model = InfluenceModel(m1, m2)" ] }, { "cell_type": "markdown", "id": "16f4ec08", "metadata": { "id": "16f4ec08" }, "source": [ "

کامپایل کردن مدل

" ] }, { "cell_type": "code", "execution_count": 7, "id": "0bbddc92", "metadata": { "id": "0bbddc92" }, "outputs": [], "source": [ "optimizer_1 = tf.optimizers.Adam(learning_rate=1e-3, beta_1=0.9)\n", "optimizer_2 = tf.optimizers.Adam(learning_rate=1e-3, beta_1=0.9)\n", "\n", "m1.compile(optimizer_1)\n", "m2.compile(optimizer_2)\n", "model.compile(optimizer_1, optimizer_2)\n" ] }, { "cell_type": "code", "execution_count": 8, "id": "b8ea93f6", "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 374 }, "id": "b8ea93f6", "outputId": "13054850-6a0c-484a-8fc1-8858d7eb0c3e" }, "outputs": [ { "data": { "text/html": [ "
Model: \"functional\"\n",
              "
\n" ], "text/plain": [ "\u001b[1mModel: \"functional\"\u001b[0m\n" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓\n",
              "┃ Layer (type)                         ┃ Output Shape                ┃         Param # ┃\n",
              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩\n",
              "│ input_layer (InputLayer)             │ (None, 28, 28, 1)           │               0 │\n",
              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
              "│ conv2d (Conv2D)                      │ (None, 26, 26, 32)          │             320 │\n",
              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
              "│ conv2d_1 (Conv2D)                    │ (None, 12, 12, 16)          │           4,624 │\n",
              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
              "│ conv2d_2 (Conv2D)                    │ (None, 10, 10, 8)           │           1,160 │\n",
              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
              "│ conv2d_3 (Conv2D)                    │ (None, 4, 4, 4)             │             292 │\n",
              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
              "│ conv2d_4 (Conv2D)                    │ (None, 1, 1, 128)           │           8,320 │\n",
              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
              "│ flatten (Flatten)                    │ (None, 128)                 │               0 │\n",
              "└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘\n",
              "
\n" ], "text/plain": [ "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓\n", "┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n", "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩\n", "│ input_layer (\u001b[38;5;33mInputLayer\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m28\u001b[0m, \u001b[38;5;34m28\u001b[0m, \u001b[38;5;34m1\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n", "│ conv2d (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m26\u001b[0m, \u001b[38;5;34m26\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m320\u001b[0m │\n", "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n", "│ conv2d_1 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m12\u001b[0m, \u001b[38;5;34m12\u001b[0m, \u001b[38;5;34m16\u001b[0m) │ \u001b[38;5;34m4,624\u001b[0m │\n", "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n", "│ conv2d_2 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m, \u001b[38;5;34m10\u001b[0m, \u001b[38;5;34m8\u001b[0m) │ \u001b[38;5;34m1,160\u001b[0m │\n", "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n", "│ conv2d_3 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m4\u001b[0m) │ \u001b[38;5;34m292\u001b[0m │\n", "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n", "│ conv2d_4 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m, \u001b[38;5;34m1\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m8,320\u001b[0m │\n", "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n", "│ flatten (\u001b[38;5;33mFlatten\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", "└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘\n" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
 Total params: 14,716 (57.48 KB)\n",
              "
\n" ], "text/plain": [ "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m14,716\u001b[0m (57.48 KB)\n" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
 Trainable params: 14,716 (57.48 KB)\n",
              "
\n" ], "text/plain": [ "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m14,716\u001b[0m (57.48 KB)\n" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
 Non-trainable params: 0 (0.00 B)\n",
              "
\n" ], "text/plain": [ "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "m1.summary()" ] }, { "cell_type": "code", "execution_count": 9, "id": "f2ea384a", "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 272 }, "id": "f2ea384a", "outputId": "9a7dc510-a44c-4d69-bc09-26fb404d89a2" }, "outputs": [ { "data": { "text/html": [ "
Model: \"functional_1\"\n",
              "
\n" ], "text/plain": [ "\u001b[1mModel: \"functional_1\"\u001b[0m\n" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓\n",
              "┃ Layer (type)                         ┃ Output Shape                ┃         Param # ┃\n",
              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩\n",
              "│ input_layer_1 (InputLayer)           │ (None, 1, 138)              │               0 │\n",
              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
              "│ lstm (LSTM)                          │ (None, 1, 64)               │          51,968 │\n",
              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
              "│ lstm_1 (LSTM)                        │ (None, 32)                  │          12,416 │\n",
              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
              "│ dense (Dense)                        │ (None, 10)                  │             330 │\n",
              "└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘\n",
              "
\n" ], "text/plain": [ "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓\n", "┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n", "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩\n", "│ input_layer_1 (\u001b[38;5;33mInputLayer\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m, \u001b[38;5;34m138\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n", "│ lstm (\u001b[38;5;33mLSTM\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m51,968\u001b[0m │\n", "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n", "│ lstm_1 (\u001b[38;5;33mLSTM\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m12,416\u001b[0m │\n", "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n", "│ dense (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m) │ \u001b[38;5;34m330\u001b[0m │\n", "└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘\n" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
 Total params: 64,714 (252.79 KB)\n",
              "
\n" ], "text/plain": [ "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m64,714\u001b[0m (252.79 KB)\n" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
 Trainable params: 64,714 (252.79 KB)\n",
              "
\n" ], "text/plain": [ "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m64,714\u001b[0m (252.79 KB)\n" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/html": [ "
 Non-trainable params: 0 (0.00 B)\n",
              "
\n" ], "text/plain": [ "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "m2.summary()" ] }, { "cell_type": "markdown", "id": "ac325eb7", "metadata": { "id": "ac325eb7" }, "source": [ "

اموزش مدل

" ] }, { "cell_type": "code", "execution_count": 10, "id": "c5e948ab", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "c5e948ab", "outputId": "558b2117-9d0d-4734-e6d8-5ae549fb0c14", "scrolled": true }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Epoch 1/3\n", "\u001b[1m1875/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m437s\u001b[0m 126ms/step - loss: 0.3255 - metric: 0.8450\n", "Epoch 2/3\n", "\u001b[1m1875/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m252s\u001b[0m 121ms/step - loss: 0.0815 - metric: 0.9786\n", "Epoch 3/3\n", "\u001b[1m1875/1875\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m272s\u001b[0m 127ms/step - loss: 0.0633 - metric: 0.9833\n" ] }, { "data": { "text/plain": [ "" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ "model.fit(train_set[0], train_set[1], epochs=3, batch_size=32)" ] }, { "cell_type": "markdown", "id": "a42879cd", "metadata": { "id": "a42879cd" }, "source": [ "

اماده سازی نمونه ها و محاسبه اهمیت هر نمونه نسبت به حضور دیگر نمونه ها

" ] }, { "cell_type": "code", "execution_count": 23, "id": "2a669978", "metadata": { "id": "2a669978" }, "outputs": [], "source": [ "def get_samples(sample_ind, batch_size=64):\n", "\n", " # اماده سازی نمونه ها\n", " sample_image = test_set[0][sample_ind:sample_ind+batch_size,...]\n", " sample_label = test_set[1][sample_ind:sample_ind+batch_size,...]\n", " return sample_image, sample_label" ] }, { "cell_type": "code", "execution_count": 24, "id": "c910c017", "metadata": { "id": "c910c017" }, "outputs": [], "source": [ "def get_imporance_function(sample_ind):\n", " loss_fnc = tf.keras.losses.SparseCategoricalCrossentropy(reduction='none', from_logits=False)\n", " img, lbl = get_samples(sample_ind, 1)\n", " def get_batch_importance(batch_ind, batch_size=64):\n", " sample_images, sample_labels = get_samples(batch_ind, batch_size)\n", " sample_images = np.concatenate([img, sample_images])\n", " sample_labels = np.concatenate([lbl, sample_labels])\n", "\n", " probs_vec, probs_mtx = model.call_at_zero([sample_images, sample_labels])\n", " samples = probs_mtx.numpy()\n", " probs_vec = probs_vec.numpy()\n", "\n", " m = samples.mean(axis=0)\n", "\n", " # حذف نمونه مورد مطالعه و مشاهده تاثیر حضور دیگر نمونه و عدم حضور نمونه بر پیس بینی\n", " sample_output = samples.sum(axis=0, keepdims=True) - samples\n", " sample_output = sample_output/(batch_size-1)\n", " loss_with_sample = loss_fnc(lbl, m)\n", " loss_without_sample = loss_fnc(tf.repeat(lbl[tf.newaxis, ...], repeats=batch_size, axis=0), sample_output)\n", " sample_importance = loss_with_sample-loss_without_sample\n", " return sample_images[1:,...], sample_importance, probs_vec, samples\n", " return get_batch_importance, img, lbl" ] }, { "cell_type": "code", "execution_count": 25, "id": "a4761918", "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "a4761918", "outputId": "1ca243ec-9aaa-4974-a37e-ced6ac5fd023" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "(64, 1, 138)\n" ] } ], "source": [ "batch_ind = 5888\n", "batch_ind = 4498\n", "batch_ind = 1522\n", "batch_ind = 625\n", "batch_ind = 9698\n", "\n", "batch_size = 64\n", "\n", "batch_ind = batch_ind+1\n", "\n", "sample_ind = batch_ind-1\n", "importance_function_batch, img, lbl = get_imporance_function(sample_ind)\n", "sample_images, importance, probs_vec, sample_output = importance_function_batch(batch_ind)" ] }, { "cell_type": "markdown", "id": "52cfc350", "metadata": { "id": "52cfc350" }, "source": [ "

مشاهده تاثیر دیگر نمونه ها بر پیش بینی مدل

" ] }, { "cell_type": "code", "execution_count": 26, "id": "7b17b3c2", "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 486 }, "id": "7b17b3c2", "outputId": "ef8a4779-5ce3-4cee-8d18-c45702d4ca5a" }, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 26, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plt.figure(figsize=(15,5))\n", "plt.subplot(121)\n", "plt.imshow(img[0])\n", "plt.title(lbl[0])\n", "plt.axis('off')\n", "\n", "plt.subplot(122)\n", "plt.plot(probs_vec, label='model probabilities')\n", "plt.plot(lbl, 1, 'rx', label='correct label')\n", "plt.legend()" ] }, { "cell_type": "code", "execution_count": 27, "id": "e1124039", "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 1000 }, "id": "e1124039", "outputId": "25b8e29e-4df6-4568-a5e1-b11add567f33" }, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "from matplotlib import pyplot as plt\n", "import numpy as np\n", "\n", "inds = np.argsort(importance)\n", "plt.figure()\n", "plt.plot(sample_output[inds[:5]].mean(axis=0))\n", "\n", "\n", "plt.figure(figsize=(15,15))\n", "for i in range(len(inds)):\n", " plt.subplot(batch_size//8+1, 8, i+1)\n", " plt.imshow(sample_images[inds[i],...])\n", " plt.title(\"%.7f\"%(importance[inds[i]]))\n", " plt.axis('off')" ] } ], "metadata": { "colab": { "provenance": [] }, "kernelspec": { "display_name": "CV", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.11.5" } }, "nbformat": 4, "nbformat_minor": 5 }