{
"cells": [
{
"cell_type": "code",
"execution_count": 4,
"id": "ec6a2fcf",
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"iskaggle = os.environ.get('KAGGLE_KERNEL_RUN_TYPE', '')"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "eee58ba4",
"metadata": {},
"outputs": [],
"source": [
"if iskaggle:\n",
" !pip install -Uqq fastai"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "da19600d",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Collecting gradio\n",
" Downloading gradio-3.1.4-py3-none-any.whl (5.6 MB)\n",
"Requirement already satisfied: matplotlib in c:\\users\\pratc\\anaconda3\\envs\\geo_env\\lib\\site-packages (from gradio) (3.4.2)\n",
"Requirement already satisfied: pillow in c:\\users\\pratc\\anaconda3\\envs\\geo_env\\lib\\site-packages (from gradio) (9.2.0)\n",
"Collecting paramiko\n",
" Downloading paramiko-2.11.0-py2.py3-none-any.whl (212 kB)\n",
"Collecting analytics-python\n",
" Downloading analytics_python-1.4.0-py2.py3-none-any.whl (15 kB)\n",
"Collecting httpx\n",
" Downloading httpx-0.23.0-py3-none-any.whl (84 kB)\n",
"Collecting pydub\n",
" Downloading pydub-0.25.1-py2.py3-none-any.whl (32 kB)\n",
"Collecting pycryptodome\n",
" Downloading pycryptodome-3.15.0-cp35-abi3-win_amd64.whl (1.9 MB)\n",
"Requirement already satisfied: requests in c:\\users\\pratc\\anaconda3\\envs\\geo_env\\lib\\site-packages (from gradio) (2.26.0)\n",
"Requirement already satisfied: pandas in c:\\users\\pratc\\anaconda3\\envs\\geo_env\\lib\\site-packages (from gradio) (1.2.4)\n",
"Requirement already satisfied: numpy in c:\\users\\pratc\\anaconda3\\envs\\geo_env\\lib\\site-packages (from gradio) (1.20.3)\n",
"Collecting uvicorn\n",
" Downloading uvicorn-0.18.2-py3-none-any.whl (57 kB)\n",
"Requirement already satisfied: aiohttp in c:\\users\\pratc\\anaconda3\\envs\\geo_env\\lib\\site-packages (from gradio) (3.8.1)\n",
"Requirement already satisfied: fsspec in c:\\users\\pratc\\anaconda3\\envs\\geo_env\\lib\\site-packages (from gradio) (2022.7.1)\n",
"Collecting fastapi\n",
" Downloading fastapi-0.79.0-py3-none-any.whl (54 kB)\n",
"Collecting ffmpy\n",
" Downloading ffmpy-0.3.0.tar.gz (4.8 kB)\n",
"Collecting python-multipart\n",
" Downloading python-multipart-0.0.5.tar.gz (32 kB)\n",
"Collecting orjson\n",
" Downloading orjson-3.7.11-cp39-none-win_amd64.whl (199 kB)\n",
"Requirement already satisfied: pydantic in c:\\users\\pratc\\anaconda3\\envs\\geo_env\\lib\\site-packages (from gradio) (1.9.1)\n",
"Collecting markdown-it-py[linkify,plugins]\n",
" Downloading markdown_it_py-2.1.0-py3-none-any.whl (84 kB)\n",
"Collecting h11<0.13,>=0.11\n",
" Downloading h11-0.12.0-py3-none-any.whl (54 kB)\n",
"Requirement already satisfied: Jinja2 in c:\\users\\pratc\\anaconda3\\envs\\geo_env\\lib\\site-packages (from gradio) (3.0.1)\n",
"Requirement already satisfied: multidict<7.0,>=4.5 in c:\\users\\pratc\\anaconda3\\envs\\geo_env\\lib\\site-packages (from aiohttp->gradio) (5.1.0)\n",
"Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in c:\\users\\pratc\\anaconda3\\envs\\geo_env\\lib\\site-packages (from aiohttp->gradio) (4.0.1)\n",
"Requirement already satisfied: frozenlist>=1.1.1 in c:\\users\\pratc\\anaconda3\\envs\\geo_env\\lib\\site-packages (from aiohttp->gradio) (1.2.0)\n",
"Requirement already satisfied: yarl<2.0,>=1.0 in c:\\users\\pratc\\anaconda3\\envs\\geo_env\\lib\\site-packages (from aiohttp->gradio) (1.6.3)\n",
"Requirement already satisfied: attrs>=17.3.0 in c:\\users\\pratc\\anaconda3\\envs\\geo_env\\lib\\site-packages (from aiohttp->gradio) (21.2.0)\n",
"Requirement already satisfied: aiosignal>=1.1.2 in c:\\users\\pratc\\anaconda3\\envs\\geo_env\\lib\\site-packages (from aiohttp->gradio) (1.2.0)\n",
"Requirement already satisfied: charset-normalizer<3.0,>=2.0 in c:\\users\\pratc\\anaconda3\\envs\\geo_env\\lib\\site-packages (from aiohttp->gradio) (2.0.0)\n",
"Requirement already satisfied: typing-extensions>=3.6.5 in c:\\users\\pratc\\anaconda3\\envs\\geo_env\\lib\\site-packages (from async-timeout<5.0,>=4.0.0a3->aiohttp->gradio) (4.1.1)\n",
"Requirement already satisfied: idna>=2.0 in c:\\users\\pratc\\anaconda3\\envs\\geo_env\\lib\\site-packages (from yarl<2.0,>=1.0->aiohttp->gradio) (3.1)\n",
"Collecting backoff==1.10.0\n",
" Downloading backoff-1.10.0-py2.py3-none-any.whl (31 kB)\n",
"Requirement already satisfied: six>=1.5 in c:\\users\\pratc\\anaconda3\\envs\\geo_env\\lib\\site-packages (from analytics-python->gradio) (1.16.0)\n",
"Collecting monotonic>=1.5\n",
" Downloading monotonic-1.6-py2.py3-none-any.whl (8.2 kB)\n",
"Requirement already satisfied: python-dateutil>2.1 in c:\\users\\pratc\\anaconda3\\envs\\geo_env\\lib\\site-packages (from analytics-python->gradio) (2.8.0)\n",
"Requirement already satisfied: certifi>=2017.4.17 in c:\\users\\pratc\\anaconda3\\envs\\geo_env\\lib\\site-packages (from requests->gradio) (2022.6.15)\n",
"Requirement already satisfied: urllib3<1.27,>=1.21.1 in c:\\users\\pratc\\anaconda3\\envs\\geo_env\\lib\\site-packages (from requests->gradio) (1.25.11)\n",
"Collecting starlette==0.19.1\n",
" Downloading starlette-0.19.1-py3-none-any.whl (63 kB)\n",
"Collecting anyio<5,>=3.4.0\n",
" Downloading anyio-3.6.1-py3-none-any.whl (80 kB)\n",
"Requirement already satisfied: sniffio>=1.1 in c:\\users\\pratc\\anaconda3\\envs\\geo_env\\lib\\site-packages (from anyio<5,>=3.4.0->starlette==0.19.1->fastapi->gradio) (1.2.0)\n",
"Collecting rfc3986[idna2008]<2,>=1.3\n",
" Downloading rfc3986-1.5.0-py2.py3-none-any.whl (31 kB)\n",
"Collecting httpcore<0.16.0,>=0.15.0\n",
" Downloading httpcore-0.15.0-py3-none-any.whl (68 kB)\n",
"Requirement already satisfied: MarkupSafe>=2.0 in c:\\users\\pratc\\anaconda3\\envs\\geo_env\\lib\\site-packages (from Jinja2->gradio) (2.0.1)\n",
"Collecting mdurl~=0.1\n",
" Downloading mdurl-0.1.1-py3-none-any.whl (10 kB)\n",
"Collecting mdit-py-plugins\n",
" Downloading mdit_py_plugins-0.3.0-py3-none-any.whl (43 kB)\n",
"Collecting linkify-it-py~=1.0\n",
" Downloading linkify_it_py-1.0.3-py3-none-any.whl (19 kB)\n",
"Collecting uc-micro-py\n",
" Downloading uc_micro_py-1.0.1-py3-none-any.whl (6.2 kB)\n",
"Requirement already satisfied: pyparsing>=2.2.1 in c:\\users\\pratc\\anaconda3\\envs\\geo_env\\lib\\site-packages (from matplotlib->gradio) (2.4.7)\n",
"Requirement already satisfied: cycler>=0.10 in c:\\users\\pratc\\anaconda3\\envs\\geo_env\\lib\\site-packages (from matplotlib->gradio) (0.10.0)\n",
"Requirement already satisfied: kiwisolver>=1.0.1 in c:\\users\\pratc\\anaconda3\\envs\\geo_env\\lib\\site-packages (from matplotlib->gradio) (1.3.1)\n",
"Requirement already satisfied: pytz>=2017.3 in c:\\users\\pratc\\anaconda3\\envs\\geo_env\\lib\\site-packages (from pandas->gradio) (2021.1)\n",
"Requirement already satisfied: cryptography>=2.5 in c:\\users\\pratc\\anaconda3\\envs\\geo_env\\lib\\site-packages (from paramiko->gradio) (3.4.7)\n",
"Collecting bcrypt>=3.1.3\n",
" Downloading bcrypt-3.2.2-cp36-abi3-win_amd64.whl (29 kB)\n",
"Collecting pynacl>=1.0.1\n",
" Downloading PyNaCl-1.5.0-cp36-abi3-win_amd64.whl (212 kB)\n",
"Requirement already satisfied: cffi>=1.1 in c:\\users\\pratc\\anaconda3\\envs\\geo_env\\lib\\site-packages (from bcrypt>=3.1.3->paramiko->gradio) (1.14.6)\n",
"Requirement already satisfied: pycparser in c:\\users\\pratc\\anaconda3\\envs\\geo_env\\lib\\site-packages (from cffi>=1.1->bcrypt>=3.1.3->paramiko->gradio) (2.20)\n",
"Requirement already satisfied: click>=7.0 in c:\\users\\pratc\\anaconda3\\envs\\geo_env\\lib\\site-packages (from uvicorn->gradio) (7.1.2)\n",
"Building wheels for collected packages: ffmpy, python-multipart\n",
" Building wheel for ffmpy (setup.py): started\n",
" Building wheel for ffmpy (setup.py): finished with status 'done'\n",
" Created wheel for ffmpy: filename=ffmpy-0.3.0-py3-none-any.whl size=4714 sha256=0a2cd8afa5eb739096057ae7854b0198eeaaaba0de9d8f56814731b246b25296\n",
" Stored in directory: c:\\users\\pratc\\appdata\\local\\pip\\cache\\wheels\\91\\e2\\96\\f676aa08bfd789328c6576cd0f1fde4a3d686703bb0c247697\n",
" Building wheel for python-multipart (setup.py): started\n",
" Building wheel for python-multipart (setup.py): finished with status 'done'\n",
" Created wheel for python-multipart: filename=python_multipart-0.0.5-py3-none-any.whl size=31675 sha256=02e1aa07aa1a7d11df9a33043fa88318299081fd8f09a5d62638281b62f4711c\n",
" Stored in directory: c:\\users\\pratc\\appdata\\local\\pip\\cache\\wheels\\fe\\04\\d1\\a10661cc45f03c3cecda50deb2d2c22f57b4e84a75b2a5987e\n",
"Successfully built ffmpy python-multipart\n",
"Installing collected packages: mdurl, uc-micro-py, rfc3986, markdown-it-py, h11, anyio, starlette, pynacl, monotonic, mdit-py-plugins, linkify-it-py, httpcore, bcrypt, backoff, uvicorn, python-multipart, pydub, pycryptodome, paramiko, orjson, httpx, ffmpy, fastapi, analytics-python, gradio\n",
" Attempting uninstall: anyio\n",
" Found existing installation: anyio 3.3.0\n",
" Uninstalling anyio-3.3.0:\n",
" Successfully uninstalled anyio-3.3.0\n",
"Successfully installed analytics-python-1.4.0 anyio-3.6.1 backoff-1.10.0 bcrypt-3.2.2 fastapi-0.79.0 ffmpy-0.3.0 gradio-3.1.4 h11-0.12.0 httpcore-0.15.0 httpx-0.23.0 linkify-it-py-1.0.3 markdown-it-py-2.1.0 mdit-py-plugins-0.3.0 mdurl-0.1.1 monotonic-1.6 orjson-3.7.11 paramiko-2.11.0 pycryptodome-3.15.0 pydub-0.25.1 pynacl-1.5.0 python-multipart-0.0.5 rfc3986-1.5.0 starlette-0.19.1 uc-micro-py-1.0.1 uvicorn-0.18.2\n"
]
}
],
"source": [
"#!pip install gradio"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "d64b5d29",
"metadata": {},
"outputs": [],
"source": [
"from fastai.vision.all import *\n",
"import gradio as gr"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "4148d3e3",
"metadata": {},
"outputs": [],
"source": [
"!pip install -Uqq fastai"
]
},
{
"cell_type": "code",
"execution_count": 32,
"id": "7c29ad37",
"metadata": {},
"outputs": [],
"source": [
"import pathlib\n",
"temp = pathlib.PosixPath\n",
"pathlib.PosixPath = pathlib.WindowsPath\n",
"\n",
"#path = \"C:/Users/pratc/Documents/GitHub/dobbyorgollum/model.pkl\"\n",
"learn = load_learner(\"model.pkl\")"
]
},
{
"cell_type": "code",
"execution_count": 33,
"id": "3c31fc05",
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": [
"PILImage mode=RGB size=192x144"
]
},
"execution_count": 33,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from IPython import display\n",
"im=PILImage.create(\"dobby.jpg\")\n",
"im.thumbnail((192,192))\n",
"im"
]
},
{
"cell_type": "code",
"execution_count": 35,
"id": "433645e9",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n"
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Wall time: 57.8 ms\n"
]
},
{
"data": {
"text/plain": [
"('Dobby', TensorBase(0), TensorBase([0.9930, 0.0070]))"
]
},
"execution_count": 35,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%time learn.predict(im)"
]
},
{
"cell_type": "code",
"execution_count": 38,
"id": "184302af",
"metadata": {},
"outputs": [],
"source": [
"categories = ('Dobby','Gollum')\n",
"\n",
"def classify_image(img):\n",
" pred,idx,probs = learn.predict(img)\n",
" return dict(zip(categories, map(float, probs)))"
]
},
{
"cell_type": "code",
"execution_count": 39,
"id": "00668d61",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n"
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/plain": [
"{'Dobby': 0.9930480122566223, 'Gollum': 0.006952027324587107}"
]
},
"execution_count": 39,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"classify_image(im)"
]
},
{
"cell_type": "code",
"execution_count": 42,
"id": "b429e7e8",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"C:\\Users\\pratc\\Anaconda3\\envs\\geo_env\\lib\\site-packages\\gradio\\inputs.py:256: UserWarning: Usage of gradio.inputs is deprecated, and will not be supported in the future, please import your component from gradio.components\n",
" warnings.warn(\n",
"C:\\Users\\pratc\\Anaconda3\\envs\\geo_env\\lib\\site-packages\\gradio\\deprecation.py:40: UserWarning: `optional` parameter is deprecated, and it has no effect\n",
" warnings.warn(value)\n",
"C:\\Users\\pratc\\Anaconda3\\envs\\geo_env\\lib\\site-packages\\gradio\\outputs.py:196: UserWarning: Usage of gradio.outputs is deprecated, and will not be supported in the future, please import your components from gradio.components\n",
" warnings.warn(\n",
"C:\\Users\\pratc\\Anaconda3\\envs\\geo_env\\lib\\site-packages\\gradio\\deprecation.py:40: UserWarning: The 'type' parameter has been deprecated. Use the Number component instead.\n",
" warnings.warn(value)\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Running on local URL: http://127.0.0.1:7861/\n",
"\n",
"To create a public link, set `share=True` in `launch()`.\n"
]
},
{
"data": {
"text/plain": [
"(, 'http://127.0.0.1:7861/', None)"
]
},
"execution_count": 42,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"text/html": [
"\n",
"\n"
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"\n",
"\n"
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"\n",
"\n"
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"\n",
"\n"
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"image = gr.inputs.Image(shape=(192,192))\n",
"label = gr.outputs.Label()\n",
"examples = [\"dobby.jpg\",\"gollum.jpg\",\"dobby1.jpg\",\"dobby2.jpg\",\"gollum1.jpg\"]\n",
"\n",
"intf = gr.Interface(fn=classify_image, inputs= image, outputs= label, examples=examples)\n",
"intf.launch(inline= False)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "6318ad86",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.9.4"
}
},
"nbformat": 4,
"nbformat_minor": 5
}