Add the model and the training notebook

alphabet_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c688ee698acb4e925a258a1617d2be42717084536c47247c928651327ba7d19
+size 91488

chatgpt_alphabet.ipynb

@@ -0,0 +1,232 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "WaYYbq814jEh"
+      },
+      "outputs": [],
+      "source": [
+        "!pip install tensorflow"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import numpy as np\n",
+        "import tensorflow as tf\n",
+        "from tensorflow.keras.models import Sequential\n",
+        "from tensorflow.keras.layers import LSTM, Dense, Embedding\n"
+      ],
+      "metadata": {
+        "id": "m1lkAOKh4nc_"
+      },
+      "execution_count": 2,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "alphabet = \"ABCDEFGHIJKLMNOPQRSTUVWXYZ\"\n",
+        "\n",
+        "# Convert alphabet to integers\n",
+        "char_to_int = dict((c, i) for i, c in enumerate(alphabet))\n",
+        "int_to_char = dict((i, c) for i, c in enumerate(alphabet))\n",
+        "\n",
+        "# Prepare dataset\n",
+        "seq_length = 1\n",
+        "dataX = []\n",
+        "dataY = []\n",
+        "for i in range(0, len(alphabet) - seq_length, 1):\n",
+        "    seq_in = alphabet[i:i + seq_length]\n",
+        "    seq_out = alphabet[i + seq_length]\n",
+        "    dataX.append([char_to_int[char] for char in seq_in])\n",
+        "    dataY.append(char_to_int[seq_out])\n",
+        "\n",
+        "X = np.reshape(dataX, (len(dataX), seq_length, 1))\n",
+        "y = tf.keras.utils.to_categorical(dataY)\n"
+      ],
+      "metadata": {
+        "id": "kjFJxMNV4oPv"
+      },
+      "execution_count": 3,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "model = Sequential()\n",
+        "model.add(LSTM(32, input_shape=(X.shape[1], X.shape[2])))\n",
+        "model.add(Dense(y.shape[1], activation='softmax'))\n",
+        "model.compile(loss='categorical_crossentropy', optimizer='adam')\n"
+      ],
+      "metadata": {
+        "id": "P9e2hWnD4pFY"
+      },
+      "execution_count": 4,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "model.fit(X, y, epochs=500, batch_size=1, verbose=2)\n"
+      ],
+      "metadata": {
+        "id": "PO31MxKH4qGb"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "for pattern in dataX:\n",
+        "    x = np.reshape(pattern, (1, len(pattern), 1))\n",
+        "    prediction = model.predict(x, verbose=0)\n",
+        "    index = np.argmax(prediction)\n",
+        "    result = int_to_char[index]\n",
+        "    seq_in = [int_to_char[value] for value in pattern]\n",
+        "    print(seq_in, \"->\", result)\n"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "bozl3EuF4q8k",
+        "outputId": "2cc54eed-8af5-4f06-d2c5-79d3ea2380f3"
+      },
+      "execution_count": 8,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "['A'] -> B\n",
+            "['B'] -> C\n",
+            "['C'] -> D\n",
+            "['D'] -> E\n",
+            "['E'] -> F\n",
+            "['F'] -> G\n",
+            "['G'] -> H\n",
+            "['H'] -> I\n",
+            "['I'] -> J\n",
+            "['J'] -> K\n",
+            "['K'] -> L\n",
+            "['L'] -> M\n",
+            "['M'] -> N\n",
+            "['N'] -> O\n",
+            "['O'] -> O\n",
+            "['P'] -> P\n",
+            "['Q'] -> R\n",
+            "['R'] -> T\n",
+            "['S'] -> T\n",
+            "['T'] -> V\n",
+            "['U'] -> V\n",
+            "['V'] -> X\n",
+            "['W'] -> Z\n",
+            "['X'] -> Z\n",
+            "['Y'] -> Z\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "model.save('alphabet_model.h5')\n",
+        "from google.colab import files\n",
+        "files.download('alphabet_model.h5')\n"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 17
+        },
+        "id": "FUCsjNyY8ZCs",
+        "outputId": "496fd160-13f1-4af1-9ae3-ea6c89513adb"
+      },
+      "execution_count": 7,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<IPython.core.display.Javascript object>"
+            ],
+            "application/javascript": [
+              "\n",
+              "    async function download(id, filename, size) {\n",
+              "      if (!google.colab.kernel.accessAllowed) {\n",
+              "        return;\n",
+              "      }\n",
+              "      const div = document.createElement('div');\n",
+              "      const label = document.createElement('label');\n",
+              "      label.textContent = `Downloading \"${filename}\": `;\n",
+              "      div.appendChild(label);\n",
+              "      const progress = document.createElement('progress');\n",
+              "      progress.max = size;\n",
+              "      div.appendChild(progress);\n",
+              "      document.body.appendChild(div);\n",
+              "\n",
+              "      const buffers = [];\n",
+              "      let downloaded = 0;\n",
+              "\n",
+              "      const channel = await google.colab.kernel.comms.open(id);\n",
+              "      // Send a message to notify the kernel that we're ready.\n",
+              "      channel.send({})\n",
+              "\n",
+              "      for await (const message of channel.messages) {\n",
+              "        // Send a message to notify the kernel that we're ready.\n",
+              "        channel.send({})\n",
+              "        if (message.buffers) {\n",
+              "          for (const buffer of message.buffers) {\n",
+              "            buffers.push(buffer);\n",
+              "            downloaded += buffer.byteLength;\n",
+              "            progress.value = downloaded;\n",
+              "          }\n",
+              "        }\n",
+              "      }\n",
+              "      const blob = new Blob(buffers, {type: 'application/binary'});\n",
+              "      const a = document.createElement('a');\n",
+              "      a.href = window.URL.createObjectURL(blob);\n",
+              "      a.download = filename;\n",
+              "      div.appendChild(a);\n",
+              "      a.click();\n",
+              "      div.remove();\n",
+              "    }\n",
+              "  "
+            ]
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<IPython.core.display.Javascript object>"
+            ],
+            "application/javascript": [
+              "download(\"download_10038af2-1923-4b7b-afba-d12d0f08f61e\", \"alphabet_model.h5\", 91488)"
+            ]
+          },
+          "metadata": {}
+        }
+      ]
+    }
+  ]
+}

chatgpt_alphabet.py

@@ -0,0 +1,53 @@
+# -*- coding: utf-8 -*-
+"""chatgpt-alphabet.ipynb
+
+Automatically generated by Colaboratory.
+
+Original file is located at
+    https://colab.research.google.com/drive/1BFy2tYkYPr7mev8Gg9AMT8ZD_Nj0hH3U
+"""
+
+# !pip install tensorflow
+
+import numpy as np
+import tensorflow as tf
+from tensorflow.keras.models import Sequential
+from tensorflow.keras.layers import LSTM, Dense, Embedding
+
+alphabet = "ABCDEFGHIJKLMNOPQRSTUVWXYZ"
+
+# Convert alphabet to integers
+char_to_int = dict((c, i) for i, c in enumerate(alphabet))
+int_to_char = dict((i, c) for i, c in enumerate(alphabet))
+
+# Prepare dataset
+seq_length = 1
+dataX = []
+dataY = []
+for i in range(0, len(alphabet) - seq_length, 1):
+    seq_in = alphabet[i:i + seq_length]
+    seq_out = alphabet[i + seq_length]
+    dataX.append([char_to_int[char] for char in seq_in])
+    dataY.append(char_to_int[seq_out])
+
+X = np.reshape(dataX, (len(dataX), seq_length, 1))
+y = tf.keras.utils.to_categorical(dataY)
+
+model = Sequential()
+model.add(LSTM(32, input_shape=(X.shape[1], X.shape[2])))
+model.add(Dense(y.shape[1], activation='softmax'))
+model.compile(loss='categorical_crossentropy', optimizer='adam')
+
+model.fit(X, y, epochs=500, batch_size=1, verbose=2)
+
+for pattern in dataX:
+    x = np.reshape(pattern, (1, len(pattern), 1))
+    prediction = model.predict(x, verbose=0)
+    index = np.argmax(prediction)
+    result = int_to_char[index]
+    seq_in = [int_to_char[value] for value in pattern]
+    print(seq_in, "->", result)
+
+model.save('alphabet_model.h5')
+from google.colab import files
+files.download('alphabet_model.h5')