Skip to content

Instantly share code, notes, and snippets.

@kiransair
Created April 24, 2024 08:01
Show Gist options
  • Save kiransair/ca718d53b64f97f81eb504676568a222 to your computer and use it in GitHub Desktop.
Save kiransair/ca718d53b64f97f81eb504676568a222 to your computer and use it in GitHub Desktop.
TF_Forum_24144.ipynb
Display the source blob
Display the rendered blob
Raw
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": [],
"authorship_tag": "ABX9TyPgjhBDdcpaSe9EuPw5lpVn",
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/gist/kiransair/ca718d53b64f97f81eb504676568a222/tf_forum_24144.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"id": "uPymGniNGgEC"
},
"outputs": [],
"source": [
"import tensorflow as tf"
]
},
{
"cell_type": "code",
"source": [
"\n",
"inputs = tf.keras.Input(shape=(28, 28, 1))\n",
"\n",
"conv1 = tf.keras.layers.Conv2D(32, kernel_size=(3, 3), activation='relu')(inputs)\n",
"\n",
"pool1 = tf.keras.layers.MaxPooling2D(pool_size=(2, 2))(conv1)\n",
"\n",
"conv2 = tf.keras.layers.Conv2D(64, kernel_size=(3, 3), activation='relu')(pool1)\n",
"\n",
"x = tf.keras.layers.GlobalAveragePooling2D()(conv2)\n",
"\n",
"x = tf.keras.layers.Dropout(0.5)(x)\n",
"\n",
"outputs = tf.keras.layers.Dense(10, activation='softmax')(x)\n",
"\n",
"model = tf.keras.Model(inputs=inputs, outputs=outputs)"
],
"metadata": {
"id": "ckXeQQp3HAh7"
},
"execution_count": 2,
"outputs": []
},
{
"cell_type": "code",
"source": [
"converter = tf.lite.TFLiteConverter.from_keras_model(model)"
],
"metadata": {
"id": "6tMHuPatHDKz"
},
"execution_count": 3,
"outputs": []
},
{
"cell_type": "code",
"source": [
"tflite_model = converter.convert()"
],
"metadata": {
"id": "Xdb_zaZNHIHY"
},
"execution_count": 4,
"outputs": []
},
{
"cell_type": "code",
"source": [
"from tensorflow import keras"
],
"metadata": {
"id": "ZdNqEgdMHNd1"
},
"execution_count": 5,
"outputs": []
},
{
"cell_type": "code",
"source": [
"model1=keras.Sequential([\n",
" keras.Input(shape=(28,28,1)),\n",
" keras.layers.Conv2D(32,kernel_size=(3,3),activation='relu',),\n",
" keras.layers.MaxPooling2D(pool_size=(2,2)),\n",
" keras.layers.Conv2D(64,kernel_size=(3,3),activation='relu'),\n",
" keras.layers.GlobalAveragePooling2D(),\n",
" keras.layers.Dropout(0.5),\n",
" keras.layers.Dense(10,activation='softmax')\n",
"])"
],
"metadata": {
"id": "zHQyXDilHKRi"
},
"execution_count": 6,
"outputs": []
},
{
"cell_type": "code",
"source": [
"converter = tf.lite.TFLiteConverter.from_keras_model(model1)"
],
"metadata": {
"id": "Ot5b9RagHRFs"
},
"execution_count": 7,
"outputs": []
},
{
"cell_type": "code",
"source": [
"tflite_model = converter.convert()"
],
"metadata": {
"id": "Sp4xWbAeHUMz"
},
"execution_count": 8,
"outputs": []
},
{
"cell_type": "code",
"source": [],
"metadata": {
"id": "UNcfKaoAHWRx"
},
"execution_count": null,
"outputs": []
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment