AI_Training.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "AI_Training.ipynb",
      "provenance": [],
      "collapsed_sections": [],
      "authorship_tag": "ABX9TyOAz2mxSMk/VlYH6LyzX6M6",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/sahil3Vedi/Self-Driving-Car-Arduino/blob/master/AI_Training.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "co51uQNZxH08",
        "colab_type": "code",
        "outputId": "4a548d86-f876-4e56-8b61-30ceb1b8b1b4",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 122
        }
      },
      "source": [
        "from google.colab import drive\n",
        "import pandas as pd\n",
        "import os\n",
        "drive.mount('/content/drive')\n",
        "import numpy as np"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Go to this URL in a browser: https://accounts.google.com/o/oauth2/auth?client_id=947318989803-6bn6qk8qdgf4n4g3pfee6491hc0brc4i.apps.googleusercontent.com&redirect_uri=urn%3aietf%3awg%3aoauth%3a2.0%3aoob&response_type=code&scope=email%20https%3a%2f%2fwww.googleapis.com%2fauth%2fdocs.test%20https%3a%2f%2fwww.googleapis.com%2fauth%2fdrive%20https%3a%2f%2fwww.googleapis.com%2fauth%2fdrive.photos.readonly%20https%3a%2f%2fwww.googleapis.com%2fauth%2fpeopleapi.readonly\n",
            "\n",
            "Enter your authorization code:\n",
            "··········\n",
            "Mounted at /content/drive\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "hxoTeedetFdL",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "X_LOC = 'drive/My Drive/Self Driving/XTRAIN.npy'\n",
        "Y_LOC = 'drive/My Drive/Self Driving/YTRAIN.npy'\n",
        "\n",
        "X_TRAIN = np.load(X_LOC)\n",
        "Y_TRAIN = np.load(Y_LOC)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Nw70iVEWxh7X",
        "colab_type": "code",
        "outputId": "53e4b66d-4d4f-426d-9c22-81a91d2b83e3",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        }
      },
      "source": [
        "import os\n",
        "import numpy as np\n",
        "from sklearn.svm import LinearSVC\n",
        "import random\n",
        "import matplotlib.pyplot as plt\n",
        "import tensorflow as tf\n",
        "from tensorflow import keras\n",
        "from tensorflow.keras import layers\n",
        "from keras.utils import to_categorical\n",
        "\n"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Using TensorFlow backend.\n"
          ],
          "name": "stderr"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "M9YCWqDHztQT",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "def preprocess(x, y):\n",
        "  x = tf.cast(x, tf.float32) / 255.0\n",
        "  y = tf.cast(y, tf.int64)\n",
        "\n",
        "  return x, y\n",
        "\n",
        "def create_dataset(xs, ys, n_classes=10):\n",
        "  ys = tf.one_hot(ys, depth=n_classes)\n",
        "  return tf.data.Dataset.from_tensor_slices((xs, ys)) \\\n",
        "    .map(preprocess) \\\n",
        "    .shuffle(len(ys)) \\\n",
        "    .batch(500)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "GVlbWl9d0AwV",
        "colab_type": "code",
        "outputId": "d2b38888-ba9d-4533-809c-47f4bb3fde38",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        }
      },
      "source": [
        "model2 = tf.keras.Sequential([\n",
        "# Adds a densely-connected layer with 64 units to the model:\n",
        "layers.Dense(10, activation='relu', input_shape=(3,)),\n",
        "# Add another:\n",
        "layers.Dense(15, activation='relu'),\n",
        "# Add an output layer with 10 output units:\n",
        "layers.Dense(3, activation='softmax')])\n",
        "\n",
        "model2.compile(optimizer=tf.keras.optimizers.Adam(0.1),\n",
        "              loss=tf.keras.losses.CategoricalCrossentropy(from_logits=True),\n",
        "              metrics=['accuracy'])\n",
        "\n",
        "model2.fit(X_TRAIN, Y_TRAIN, epochs=100, batch_size=32)"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Epoch 1/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 1.1646 - accuracy: 0.3868\n",
            "Epoch 2/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 3/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 4/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 5/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 6/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 7/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 8/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 9/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 10/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 11/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 12/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 13/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 14/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 15/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 16/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 17/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 18/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 19/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 20/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 21/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 22/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 23/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 24/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 25/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 26/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 27/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 28/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 29/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 30/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 31/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 32/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 33/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 34/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 35/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 36/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 37/100\n",
            "4/4 [==============================] - 0s 3ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 38/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 39/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 40/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 41/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 42/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 43/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 44/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 45/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 46/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 47/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 48/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 49/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 50/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 51/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 52/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 53/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 54/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 55/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 56/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 57/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 58/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 59/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 60/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 61/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 62/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 63/100\n",
            "4/4 [==============================] - 0s 3ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 64/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 65/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 66/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 67/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 68/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 69/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 70/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 71/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 72/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 73/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 74/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 75/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 76/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 77/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 78/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 79/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 80/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 81/100\n",
            "4/4 [==============================] - 0s 3ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 82/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 83/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 84/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 85/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 86/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 87/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 88/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 89/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 90/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 91/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 92/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 93/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 94/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 95/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 96/100\n",
            "4/4 [==============================] - 0s 1ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 97/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 98/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 99/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n",
            "Epoch 100/100\n",
            "4/4 [==============================] - 0s 2ms/step - loss: 0.6930 - accuracy: 0.8585\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<tensorflow.python.keras.callbacks.History at 0x7f3206cad1d0>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 5
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "3k0IGT_-41C3",
        "colab_type": "code",
        "outputId": "c12a0ec9-0679-4726-85c7-ac40775de925",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 255
        }
      },
      "source": [
        "model2.summary()"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Model: \"sequential\"\n",
            "_________________________________________________________________\n",
            "Layer (type)                 Output Shape              Param #   \n",
            "=================================================================\n",
            "dense (Dense)                (None, 10)                40        \n",
            "_________________________________________________________________\n",
            "dense_1 (Dense)              (None, 15)                165       \n",
            "_________________________________________________________________\n",
            "dense_2 (Dense)              (None, 3)                 48        \n",
            "=================================================================\n",
            "Total params: 253\n",
            "Trainable params: 253\n",
            "Non-trainable params: 0\n",
            "_________________________________________________________________\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "isr6Gduc-DR1",
        "colab_type": "code",
        "outputId": "6c9b6a9f-7832-43b7-9f63-5b8a86d11123",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 71
        }
      },
      "source": [
        "weights = []\n",
        "biases = []\n",
        "\n",
        "for i in range(len(model2.layers)):\n",
        "  weightMx = model2.layers[i].get_weights()\n",
        "  weights.append(weightMx[0])\n",
        "  biases.append(weightMx[1])\n",
        "\n",
        "rounded_weights = []\n",
        "rounded_biases = []\n",
        "\n",
        "for j in weights:\n",
        "  Wtemp = []\n",
        "  for x in j:\n",
        "    temp = [round(n,1) for n in x]\n",
        "    Wtemp.append(temp)\n",
        "  rounded_weights.append(Wtemp)\n",
        "\n",
        "for k in biases:\n",
        "  temp = [round(n,1) for n in k]\n",
        "  rounded_biases.append(temp)\n",
        "\n",
        "print(rounded_weights)\n",
        "print(rounded_biases)"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[[[-0.2, 0.7, -0.5, -0.1, 1.0, 0.0, -0.6, -0.3, -0.2, -0.3], [0.6, -0.1, -0.3, 0.7, 0.2, -0.1, 0.2, -0.3, 0.5, 0.2], [0.4, 0.6, -0.5, -0.1, 0.8, -0.9, -0.4, 0.5, -0.0, -0.4]], [[0.2, 0.2, -0.1, -0.0, 0.1, -0.2, 0.2, -0.2, -0.2, -0.3, -0.1, 0.0, 0.5, -0.1, 0.1], [-0.6, -0.4, 1.0, -0.7, 0.4, 0.1, -0.3, 0.2, -0.0, 0.1, 0.1, -0.4, -0.3, -0.5, -0.7], [-0.4, -0.2, -0.3, 0.2, -0.5, -0.1, 0.1, 0.1, -0.2, -0.0, -0.2, -0.4, -0.2, -0.1, 0.5], [-0.5, -0.1, -0.4, -0.3, 0.2, 0.2, 0.3, -0.1, 0.3, -0.3, -0.3, 0.3, -0.1, 0.0, -0.1], [-0.2, -0.0, 1.1, -0.9, -0.1, 0.1, -0.9, 0.8, -0.4, -0.2, -0.2, -0.4, -0.3, -0.3, -0.6], [-0.5, -0.5, 0.3, -0.1, -0.3, -0.1, -0.5, 0.7, -0.3, -0.3, -0.1, 0.2, -0.6, 0.2, -0.1], [0.1, -0.4, 0.4, 0.0, 0.2, -0.5, -0.2, 0.3, 0.4, -0.4, 0.5, -0.3, -0.1, -0.1, -0.3], [-0.0, 0.3, 0.2, -0.3, -0.1, 0.2, -0.2, -0.4, -0.4, 0.3, -0.0, 0.3, -0.1, -0.2, -0.2], [-0.4, -0.2, 0.0, -0.0, -0.0, -0.2, 0.5, -0.1, 0.0, 0.2, -0.4, 0.3, -0.1, -0.0, -0.0], [-0.9, -0.3, 0.6, 0.0, 0.1, -0.5, -0.2, 0.9, 0.1, -0.4, 0.0, -0.5, -0.8, -0.4, -0.6]], [[0.5, 0.3, -0.5], [-0.3, 0.2, 0.2], [-0.5, 1.2, -0.7], [-0.1, 0.3, -0.7], [-0.5, 0.0, 0.3], [-0.4, 0.3, -0.1], [-0.1, 0.9, -0.1], [-0.6, 0.6, -0.6], [0.4, 0.4, -0.2], [0.4, 0.2, -0.2], [-0.2, -0.2, 0.3], [-0.4, 0.0, -0.5], [0.2, -0.0, -0.9], [-0.4, -0.5, 0.4], [1.1, 0.5, -0.1]]]\n",
            "[[0.0, 0.5, 0.0, 0.0, 0.5, -0.5, 0.0, -0.0, 0.0, -0.5], [-0.2, 0.0, 0.6, -0.5, 0.0, 0.0, -0.5, 0.4, 0.0, 0.0, 0.0, 0.0, -0.1, 0.0, -0.1], [-0.5, 0.6, -0.5]]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "_9Ab6mTMLpjQ",
        "colab_type": "code",
        "outputId": "0bb0ae74-1c60-4749-fb4b-ec6c48ae74f5",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 850
        }
      },
      "source": [
        "#saving weights and biases to txt file\n",
        "\n",
        "txt_weight_1 = \"{\"\n",
        "for each_vector in rounded_weights[0]:\n",
        "  new_line = \"\\n\\t{\"\n",
        "  for each_element in each_vector:\n",
        "    new_line += str(each_element)\n",
        "    new_line += \",\"\n",
        "  new_line = new_line[:-1]\n",
        "  txt_weight_1 += new_line\n",
        "  txt_weight_1 += \"},\"\n",
        "txt_weight_1 = txt_weight_1[:-1]\n",
        "txt_weight_1 += \"\\n}\"\n",
        "\n",
        "txt_weight_2 = \"{\"\n",
        "for each_vector in rounded_weights[1]:\n",
        "  new_line = \"\\n\\t{\"\n",
        "  for each_element in each_vector:\n",
        "    new_line += str(each_element)\n",
        "    new_line += \",\"\n",
        "  new_line = new_line[:-1]\n",
        "  txt_weight_2 += new_line\n",
        "  txt_weight_2 += \"},\"\n",
        "txt_weight_2 = txt_weight_2[:-1]\n",
        "txt_weight_2 += \"\\n}\"\n",
        "\n",
        "txt_weight_3 = \"{\"\n",
        "for each_vector in rounded_weights[2]:\n",
        "  new_line = \"\\n\\t{\"\n",
        "  for each_element in each_vector:\n",
        "    new_line += str(each_element)\n",
        "    new_line += \",\"\n",
        "  new_line = new_line[:-1]\n",
        "  txt_weight_3 += new_line\n",
        "  txt_weight_3 += \"},\"\n",
        "txt_weight_3 = txt_weight_3[:-1]\n",
        "txt_weight_3 += \"\\n}\"\n",
        "\n",
        "print(\"float Weights1[\"+str(len(rounded_weights[0]))+\"][\"+str(len(rounded_weights[0][0]))+\"]=\")\n",
        "print(txt_weight_1)\n",
        "print(\"float Weights2[\"+str(len(rounded_weights[1]))+\"][\"+str(len(rounded_weights[1][0]))+\"]=\")\n",
        "print(txt_weight_2)\n",
        "print(\"float Weights3[\"+str(len(rounded_weights[2]))+\"][\"+str(len(rounded_weights[2][0]))+\"]=\")\n",
        "print(txt_weight_3)\n",
        "\n",
        "txt_bias_1 = \"{\\n\\t{\"\n",
        "for each_element in rounded_biases[0]:\n",
        "  txt_bias_1 += str(each_element)\n",
        "  txt_bias_1 += \",\"\n",
        "txt_bias_1 = txt_bias_1[:-1]\n",
        "txt_bias_1 += \"}\\n}\"\n",
        "\n",
        "txt_bias_2 = \"{\\n\\t{\"\n",
        "for each_element in rounded_biases[1]:\n",
        "  txt_bias_2 += str(each_element)\n",
        "  txt_bias_2 += \",\"\n",
        "txt_bias_2 = txt_bias_2[:-1]\n",
        "txt_bias_2 += \"}\\n}\"\n",
        "\n",
        "txt_bias_3 = \"{\\n\\t{\"\n",
        "for each_element in rounded_biases[2]:\n",
        "  txt_bias_3 += str(int(each_element*10))\n",
        "  txt_bias_3 += \",\"\n",
        "txt_bias_3 = txt_bias_3[:-1]\n",
        "txt_bias_3 += \"}\\n}\"\n",
        "\n",
        "print(\"float Bias1[1][\"+str(len(rounded_biases[0]))+\"]=\")\n",
        "print(txt_bias_1)\n",
        "print(\"float Bias2[1][\"+str(len(rounded_biases[1]))+\"]=\")\n",
        "print(txt_bias_2)\n",
        "print(\"float Bias3[1][\"+str(len(rounded_biases[2]))+\"]=\")\n",
        "print(txt_bias_3)"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "float Weights1[3][10]=\n",
            "{\n",
            "\t{-0.2,0.7,-0.5,-0.1,1.0,0.0,-0.6,-0.3,-0.2,-0.3},\n",
            "\t{0.6,-0.1,-0.3,0.7,0.2,-0.1,0.2,-0.3,0.5,0.2},\n",
            "\t{0.4,0.6,-0.5,-0.1,0.8,-0.9,-0.4,0.5,-0.0,-0.4}\n",
            "}\n",
            "float Weights2[10][15]=\n",
            "{\n",
            "\t{0.2,0.2,-0.1,-0.0,0.1,-0.2,0.2,-0.2,-0.2,-0.3,-0.1,0.0,0.5,-0.1,0.1},\n",
            "\t{-0.6,-0.4,1.0,-0.7,0.4,0.1,-0.3,0.2,-0.0,0.1,0.1,-0.4,-0.3,-0.5,-0.7},\n",
            "\t{-0.4,-0.2,-0.3,0.2,-0.5,-0.1,0.1,0.1,-0.2,-0.0,-0.2,-0.4,-0.2,-0.1,0.5},\n",
            "\t{-0.5,-0.1,-0.4,-0.3,0.2,0.2,0.3,-0.1,0.3,-0.3,-0.3,0.3,-0.1,0.0,-0.1},\n",
            "\t{-0.2,-0.0,1.1,-0.9,-0.1,0.1,-0.9,0.8,-0.4,-0.2,-0.2,-0.4,-0.3,-0.3,-0.6},\n",
            "\t{-0.5,-0.5,0.3,-0.1,-0.3,-0.1,-0.5,0.7,-0.3,-0.3,-0.1,0.2,-0.6,0.2,-0.1},\n",
            "\t{0.1,-0.4,0.4,0.0,0.2,-0.5,-0.2,0.3,0.4,-0.4,0.5,-0.3,-0.1,-0.1,-0.3},\n",
            "\t{-0.0,0.3,0.2,-0.3,-0.1,0.2,-0.2,-0.4,-0.4,0.3,-0.0,0.3,-0.1,-0.2,-0.2},\n",
            "\t{-0.4,-0.2,0.0,-0.0,-0.0,-0.2,0.5,-0.1,0.0,0.2,-0.4,0.3,-0.1,-0.0,-0.0},\n",
            "\t{-0.9,-0.3,0.6,0.0,0.1,-0.5,-0.2,0.9,0.1,-0.4,0.0,-0.5,-0.8,-0.4,-0.6}\n",
            "}\n",
            "float Weights3[15][3]=\n",
            "{\n",
            "\t{0.5,0.3,-0.5},\n",
            "\t{-0.3,0.2,0.2},\n",
            "\t{-0.5,1.2,-0.7},\n",
            "\t{-0.1,0.3,-0.7},\n",
            "\t{-0.5,0.0,0.3},\n",
            "\t{-0.4,0.3,-0.1},\n",
            "\t{-0.1,0.9,-0.1},\n",
            "\t{-0.6,0.6,-0.6},\n",
            "\t{0.4,0.4,-0.2},\n",
            "\t{0.4,0.2,-0.2},\n",
            "\t{-0.2,-0.2,0.3},\n",
            "\t{-0.4,0.0,-0.5},\n",
            "\t{0.2,-0.0,-0.9},\n",
            "\t{-0.4,-0.5,0.4},\n",
            "\t{1.1,0.5,-0.1}\n",
            "}\n",
            "float Bias1[1][10]=\n",
            "{\n",
            "\t{0.0,0.5,0.0,0.0,0.5,-0.5,0.0,-0.0,0.0,-0.5}\n",
            "}\n",
            "float Bias2[1][15]=\n",
            "{\n",
            "\t{-0.2,0.0,0.6,-0.5,0.0,0.0,-0.5,0.4,0.0,0.0,0.0,0.0,-0.1,0.0,-0.1}\n",
            "}\n",
            "float Bias3[1][3]=\n",
            "{\n",
            "\t{-5,6,-5}\n",
            "}\n"
          ],
          "name": "stdout"
        }
      ]
    }
  ]
}