{
"cells": [
{
"cell_type": "code",
"execution_count": 23,
"id": "1c7dfe62-667c-47fc-a67d-9a5b97e78bee",
"metadata": {},
"outputs": [],
"source": [
"#|export\n",
"from fastai.vision.all import *\n",
"import gradio as gr"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "571f79b9-b8fa-4fba-82bf-916966fe4cb5",
"metadata": {},
"outputs": [],
"source": [
"def is_cat(x): return x[0].isUpper()"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "8f4d12e7-aee7-4085-9feb-45c0da47eb8a",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[Errno 2] No such file or directory: 'norituh'\n",
"/home/q/norituh\n"
]
}
],
"source": [
"%cd norituh"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "ba16fe63-4822-4ab4-9ef6-51c72ea67650",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": [
"PILImage mode=RGB size=144x192"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"im = PILImage.create('dog.jpg')\n",
"im.thumbnail((192, 192))\n",
"im"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "e3db311a-0702-4166-b7b2-81636daaf574",
"metadata": {},
"outputs": [],
"source": [
"#|export\n",
"learn = load_learner('model.pkl')"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "081ee4f2-759d-479a-84e3-d88ced963208",
"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": [
"CPU times: user 276 ms, sys: 0 ns, total: 276 ms\n",
"Wall time: 68.5 ms\n"
]
},
{
"data": {
"text/plain": [
"('False', TensorBase(0), TensorBase([1.0000e+00, 1.2781e-06]))"
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"%time learn.predict(im)"
]
},
{
"cell_type": "code",
"execution_count": 19,
"id": "cc62a398-bbd4-4b36-a8a1-413a46b5bb55",
"metadata": {},
"outputs": [],
"source": [
"#|export\n",
"categories = ('Dog', 'Cat')\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": 20,
"id": "95a830c9-0edc-4b53-b405-f8a47773f23b",
"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": [
"{'Dog': 0.9999986886978149, 'Cat': 1.2781407576767378e-06}"
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"classify_image(im)"
]
},
{
"cell_type": "code",
"execution_count": 21,
"id": "409f6976-8cc0-4a4f-9bdb-43fb5cd71f71",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/q/miniconda3/lib/python3.9/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",
"/home/q/miniconda3/lib/python3.9/site-packages/gradio/deprecation.py:40: UserWarning: `optional` parameter is deprecated, and it has no effect\n",
" warnings.warn(value)\n",
"/home/q/miniconda3/lib/python3.9/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",
"/home/q/miniconda3/lib/python3.9/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",
"Running on public URL: https://22407.gradio.app\n",
"\n",
"This share link expires in 72 hours. For free permanent hosting, check out Spaces: https://huggingface.co/spaces\n"
]
},
{
"data": {
"text/plain": [
"(,\n",
" 'http://127.0.0.1:7861/',\n",
" 'https://22407.gradio.app')"
]
},
"execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#|export\n",
"image = gr.inputs.Image(shape=(192, 192))\n",
"label = gr.outputs.Label()\n",
"examples = ['dog.jpg', 'cat.jpg']\n",
"\n",
"intf = gr.Interface(fn=classify_image, inputs = image, outputs=label, examples=examples)\n",
"intf.launch(inline=False, share=True)"
]
},
{
"cell_type": "code",
"execution_count": 22,
"id": "ea082bfc-b6d5-4ac8-945a-a53cd4a45cac",
"metadata": {},
"outputs": [
{
"ename": "ImportError",
"evalue": "cannot import name 'notebook2script' from 'nbdev.export' (/home/q/miniconda3/lib/python3.9/site-packages/nbdev/export.py)",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mImportError\u001b[0m Traceback (most recent call last)",
"Input \u001b[0;32mIn [22]\u001b[0m, in \u001b[0;36m| \u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mnbdev\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mexport\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m notebook2script\n",
"\u001b[0;31mImportError\u001b[0m: cannot import name 'notebook2script' from 'nbdev.export' (/home/q/miniconda3/lib/python3.9/site-packages/nbdev/export.py)"
]
},
{
"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"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Traceback (most recent call last):\n",
" File \"/home/q/miniconda3/lib/python3.9/site-packages/gradio/routes.py\", line 248, in run_predict\n",
" output = await app.blocks.process_api(\n",
" File \"/home/q/miniconda3/lib/python3.9/site-packages/gradio/blocks.py\", line 643, in process_api\n",
" predictions, duration = await self.call_function(fn_index, processed_input)\n",
" File \"/home/q/miniconda3/lib/python3.9/site-packages/gradio/blocks.py\", line 556, in call_function\n",
" prediction = await block_fn.fn(*processed_input)\n",
" File \"/home/q/miniconda3/lib/python3.9/site-packages/gradio/interface.py\", line 655, in submit_func\n",
" prediction = await self.run_prediction(args)\n",
" File \"/home/q/miniconda3/lib/python3.9/site-packages/gradio/interface.py\", line 684, in run_prediction\n",
" prediction = await anyio.to_thread.run_sync(\n",
" File \"/home/q/miniconda3/lib/python3.9/site-packages/anyio/to_thread.py\", line 28, in run_sync\n",
" return await get_asynclib().run_sync_in_worker_thread(func, *args, cancellable=cancellable,\n",
" File \"/home/q/miniconda3/lib/python3.9/site-packages/anyio/_backends/_asyncio.py\", line 818, in run_sync_in_worker_thread\n",
" return await future\n",
" File \"/home/q/miniconda3/lib/python3.9/site-packages/anyio/_backends/_asyncio.py\", line 754, in run\n",
" result = context.run(func, *args)\n",
" File \"/tmp/ipykernel_18179/2178911619.py\", line 5, in classify_image\n",
" pred, idx, probs = learn.predict(img)\n",
" File \"/home/q/miniconda3/lib/python3.9/site-packages/fastai/learner.py\", line 302, in predict\n",
" dl = self.dls.test_dl([item], rm_type_tfms=rm_type_tfms, num_workers=0)\n",
" File \"/home/q/miniconda3/lib/python3.9/site-packages/fastai/data/core.py\", line 532, in test_dl\n",
" test_ds = test_set(self.valid_ds, test_items, rm_tfms=rm_type_tfms, with_labels=with_labels\n",
" File \"/home/q/miniconda3/lib/python3.9/site-packages/fastai/data/core.py\", line 511, in test_set\n",
" if rm_tfms is None: rm_tfms = [tl.infer_idx(get_first(test_items)) for tl in test_tls]\n",
" File \"/home/q/miniconda3/lib/python3.9/site-packages/fastai/data/core.py\", line 511, in \n",
" if rm_tfms is None: rm_tfms = [tl.infer_idx(get_first(test_items)) for tl in test_tls]\n",
" File \"/home/q/miniconda3/lib/python3.9/site-packages/fastai/data/core.py\", line 405, in infer_idx\n",
" assert idx < len(self.types), f\"Expected an input of type in \\n{pretty_types}\\n but got {type(x)}\"\n",
"AssertionError: Expected an input of type in \n",
" - \n",
" - \n",
" - \n",
" - \n",
" - \n",
" - \n",
" - \n",
" but got \n"
]
},
{
"data": {
"text/html": [
"\n",
"\n"
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Traceback (most recent call last):\n",
" File \"/home/q/miniconda3/lib/python3.9/site-packages/gradio/routes.py\", line 248, in run_predict\n",
" output = await app.blocks.process_api(\n",
" File \"/home/q/miniconda3/lib/python3.9/site-packages/gradio/blocks.py\", line 643, in process_api\n",
" predictions, duration = await self.call_function(fn_index, processed_input)\n",
" File \"/home/q/miniconda3/lib/python3.9/site-packages/gradio/blocks.py\", line 556, in call_function\n",
" prediction = await block_fn.fn(*processed_input)\n",
" File \"/home/q/miniconda3/lib/python3.9/site-packages/gradio/interface.py\", line 655, in submit_func\n",
" prediction = await self.run_prediction(args)\n",
" File \"/home/q/miniconda3/lib/python3.9/site-packages/gradio/interface.py\", line 684, in run_prediction\n",
" prediction = await anyio.to_thread.run_sync(\n",
" File \"/home/q/miniconda3/lib/python3.9/site-packages/anyio/to_thread.py\", line 28, in run_sync\n",
" return await get_asynclib().run_sync_in_worker_thread(func, *args, cancellable=cancellable,\n",
" File \"/home/q/miniconda3/lib/python3.9/site-packages/anyio/_backends/_asyncio.py\", line 818, in run_sync_in_worker_thread\n",
" return await future\n",
" File \"/home/q/miniconda3/lib/python3.9/site-packages/anyio/_backends/_asyncio.py\", line 754, in run\n",
" result = context.run(func, *args)\n",
" File \"/tmp/ipykernel_18179/2178911619.py\", line 5, in classify_image\n",
" pred, idx, probs = learn.predict(img)\n",
" File \"/home/q/miniconda3/lib/python3.9/site-packages/fastai/learner.py\", line 302, in predict\n",
" dl = self.dls.test_dl([item], rm_type_tfms=rm_type_tfms, num_workers=0)\n",
" File \"/home/q/miniconda3/lib/python3.9/site-packages/fastai/data/core.py\", line 532, in test_dl\n",
" test_ds = test_set(self.valid_ds, test_items, rm_tfms=rm_type_tfms, with_labels=with_labels\n",
" File \"/home/q/miniconda3/lib/python3.9/site-packages/fastai/data/core.py\", line 511, in test_set\n",
" if rm_tfms is None: rm_tfms = [tl.infer_idx(get_first(test_items)) for tl in test_tls]\n",
" File \"/home/q/miniconda3/lib/python3.9/site-packages/fastai/data/core.py\", line 511, in \n",
" if rm_tfms is None: rm_tfms = [tl.infer_idx(get_first(test_items)) for tl in test_tls]\n",
" File \"/home/q/miniconda3/lib/python3.9/site-packages/fastai/data/core.py\", line 405, in infer_idx\n",
" assert idx < len(self.types), f\"Expected an input of type in \\n{pretty_types}\\n but got {type(x)}\"\n",
"AssertionError: Expected an input of type in \n",
" - \n",
" - \n",
" - \n",
" - \n",
" - \n",
" - \n",
" - \n",
" but got \n"
]
},
{
"data": {
"text/html": [
"\n",
"\n"
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"from nbdev.export import notebook2script"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "861a3b09-6c3b-4626-8e08-382c24bd3542",
"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": "3.9.12"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|