added mode_training.ipynb

model_training.ipynb

@@ -0,0 +1,733 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# #hide\n",
+    "# ! [ -e /content ] && pip install -Uqq fastbook\n",
+    "# import fastbook\n",
+    "# fastbook.setup_book()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#hide\n",
+    "from fastbook import *\n",
+    "from fastai.vision.widgets import *"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# From Model to Production"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## The Practice of Deep Learning"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Starting Your Project"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### The State of Deep Learning"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Computer vision"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Text (natural language processing)"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Combining text and images"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Tabular data"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Recommendation systems"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Other data types"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### The Drivetrain Approach"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Gathering Data"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# clean\n",
+    "To download images with Bing Image Search, sign up at [Microsoft Azure](https://azure.microsoft.com/en-us/services/cognitive-services/bing-web-search-api/) for a free account. You will be given a key, which you can copy and enter in a cell as follows (replacing 'XXX' with your key and executing it):"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "key = os.environ.get('AZURE_SEARCH_KEY', 'XXX')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "search_images_bing"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "results = search_images_bing(key, 'grizzly bear')\n",
+    "ims = results.attrgot('contentUrl')\n",
+    "len(ims)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#hide\n",
+    "ims = ['http://3.bp.blogspot.com/-S1scRCkI3vY/UHzV2kucsPI/AAAAAAAAA-k/YQ5UzHEm9Ss/s1600/Grizzly%2BBear%2BWildlife.jpg']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dest = 'images/grizzly.jpg'\n",
+    "download_url(ims[0], dest)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "im = Image.open(dest)\n",
+    "im.to_thumb(128,128)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "bear_types = 'grizzly','black','teddy'\n",
+    "path = Path('bears')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "if not path.exists():\n",
+    "    path.mkdir()\n",
+    "    for o in bear_types:\n",
+    "        dest = (path/o)\n",
+    "        dest.mkdir(exist_ok=True)\n",
+    "        results = search_images_bing(key, f'{o} bear')\n",
+    "        download_images(dest, urls=results.attrgot('contentUrl'))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fns = get_image_files(path)\n",
+    "fns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "failed = verify_images(fns)\n",
+    "failed"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "failed.map(Path.unlink);"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Sidebar: Getting Help in Jupyter Notebooks"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### End sidebar"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## From Data to DataLoaders"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "bears = DataBlock(\n",
+    "    blocks=(ImageBlock, CategoryBlock), \n",
+    "    get_items=get_image_files, \n",
+    "    splitter=RandomSplitter(valid_pct=0.2, seed=42),\n",
+    "    get_y=parent_label,\n",
+    "    item_tfms=Resize(128))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dls = bears.dataloaders(path)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dls.valid.show_batch(max_n=4, nrows=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "bears = bears.new(item_tfms=Resize(128, ResizeMethod.Squish))\n",
+    "dls = bears.dataloaders(path)\n",
+    "dls.valid.show_batch(max_n=4, nrows=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "bears = bears.new(item_tfms=Resize(128, ResizeMethod.Pad, pad_mode='zeros'))\n",
+    "dls = bears.dataloaders(path)\n",
+    "dls.valid.show_batch(max_n=4, nrows=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "bears = bears.new(item_tfms=RandomResizedCrop(128, min_scale=0.3))\n",
+    "dls = bears.dataloaders(path)\n",
+    "dls.train.show_batch(max_n=4, nrows=1, unique=True)"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Data Augmentation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "bears = bears.new(item_tfms=Resize(128), batch_tfms=aug_transforms(mult=2))\n",
+    "dls = bears.dataloaders(path)\n",
+    "dls.train.show_batch(max_n=8, nrows=2, unique=True)"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Training Your Model, and Using It to Clean Your Data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "bears = bears.new(\n",
+    "    item_tfms=RandomResizedCrop(224, min_scale=0.5),\n",
+    "    batch_tfms=aug_transforms())\n",
+    "dls = bears.dataloaders(path)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "learn = vision_learner(dls, resnet18, metrics=error_rate)\n",
+    "learn.fine_tune(4)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "interp = ClassificationInterpretation.from_learner(learn)\n",
+    "interp.plot_confusion_matrix()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "interp.plot_top_losses(5, nrows=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "cleaner = ImageClassifierCleaner(learn)\n",
+    "cleaner"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#hide\n",
+    "# for idx in cleaner.delete(): cleaner.fns[idx].unlink()\n",
+    "# for idx,cat in cleaner.change(): shutil.move(str(cleaner.fns[idx]), path/cat)"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Turning Your Model into an Online Application"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Using the Model for Inference"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "learn.export()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "path = Path()\n",
+    "path.ls(file_exts='.pkl')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "learn_inf = load_learner(path/'export.pkl')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "learn_inf.predict('images/grizzly.jpg')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "learn_inf.dls.vocab"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Creating a Notebook App from the Model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "btn_upload = widgets.FileUpload()\n",
+    "btn_upload"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#hide\n",
+    "# For the book, we can't actually click an upload button, so we fake it\n",
+    "btn_upload = SimpleNamespace(data = ['images/grizzly.jpg'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "img = PILImage.create(btn_upload.data[-1])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "out_pl = widgets.Output()\n",
+    "out_pl.clear_output()\n",
+    "with out_pl: display(img.to_thumb(128,128))\n",
+    "out_pl"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pred,pred_idx,probs = learn_inf.predict(img)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "lbl_pred = widgets.Label()\n",
+    "lbl_pred.value = f'Prediction: {pred}; Probability: {probs[pred_idx]:.04f}'\n",
+    "lbl_pred"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "btn_run = widgets.Button(description='Classify')\n",
+    "btn_run"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def on_click_classify(change):\n",
+    "    img = PILImage.create(btn_upload.data[-1])\n",
+    "    out_pl.clear_output()\n",
+    "    with out_pl: display(img.to_thumb(128,128))\n",
+    "    pred,pred_idx,probs = learn_inf.predict(img)\n",
+    "    lbl_pred.value = f'Prediction: {pred}; Probability: {probs[pred_idx]:.04f}'\n",
+    "\n",
+    "btn_run.on_click(on_click_classify)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#hide\n",
+    "#Putting back btn_upload to a widget for next cell\n",
+    "btn_upload = widgets.FileUpload()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "VBox([widgets.Label('Select your bear!'), \n",
+    "      btn_upload, btn_run, out_pl, lbl_pred])"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Turning Your Notebook into a Real App"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#hide\n",
+    "# !pip install voila\n",
+    "# !jupyter serverextension enable --sys-prefix voila "
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Deploying your app"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## How to Avoid Disaster"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Unforeseen Consequences and Feedback Loops"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Get Writing!"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Questionnaire"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "1. Provide an example of where the bear classification model might work poorly in production, due to structural or style differences in the training data.\n",
+    "1. Where do text models currently have a major deficiency?\n",
+    "1. What are possible negative societal implications of text generation models?\n",
+    "1. In situations where a model might make mistakes, and those mistakes could be harmful, what is a good alternative to automating a process?\n",
+    "1. What kind of tabular data is deep learning particularly good at?\n",
+    "1. What's a key downside of directly using a deep learning model for recommendation systems?\n",
+    "1. What are the steps of the Drivetrain Approach?\n",
+    "1. How do the steps of the Drivetrain Approach map to a recommendation system?\n",
+    "1. Create an image recognition model using data you curate, and deploy it on the web.\n",
+    "1. What is `DataLoaders`?\n",
+    "1. What four things do we need to tell fastai to create `DataLoaders`?\n",
+    "1. What does the `splitter` parameter to `DataBlock` do?\n",
+    "1. How do we ensure a random split always gives the same validation set?\n",
+    "1. What letters are often used to signify the independent and dependent variables?\n",
+    "1. What's the difference between the crop, pad, and squish resize approaches? When might you choose one over the others?\n",
+    "1. What is data augmentation? Why is it needed?\n",
+    "1. What is the difference between `item_tfms` and `batch_tfms`?\n",
+    "1. What is a confusion matrix?\n",
+    "1. What does `export` save?\n",
+    "1. What is it called when we use a model for getting predictions, instead of training?\n",
+    "1. What are IPython widgets?\n",
+    "1. When might you want to use CPU for deployment? When might GPU be better?\n",
+    "1. What are the downsides of deploying your app to a server, instead of to a client (or edge) device such as a phone or PC?\n",
+    "1. What are three examples of problems that could occur when rolling out a bear warning system in practice?\n",
+    "1. What is \"out-of-domain data\"?\n",
+    "1. What is \"domain shift\"?\n",
+    "1. What are the three steps in the deployment process?"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Further Research"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "1. Consider how the Drivetrain Approach maps to a project or problem you're interested in.\n",
+    "1. When might it be best to avoid certain types of data augmentation?\n",
+    "1. For a project you're interested in applying deep learning to, consider the thought experiment \"What would happen if it went really, really well?\"\n",
+    "1. Start a blog, and write your first blog post. For instance, write about what you think deep learning might be useful for in a domain you're interested in."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "jupytext": {
+   "split_at_heading": true
+  },
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

tips.ipynb

@@ -0,0 +1,155 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Tips:\n",
+    "## downloading images using duckduckgo and fastbook"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "/home/demonhunter/git/fastbook_tests/damaged_car_detection\n"
+     ]
+    }
+   ],
+   "source": [
+    "\n",
+    "import os \n",
+    "print(os.getcwd())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "slideshow": {
+     "slide_type": "slide"
+    },
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "5"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#| export\n",
+    "from fastbook import *\n",
+    "\n",
+    "query = \"joker\"\n",
+    "\n",
+    "urls = search_images_ddg(query, max_images = 5 )\n",
+    "\n",
+    "len(urls)\n",
+    "#| export \n",
+    "# for url in urls : print(url)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "metadata": {
+    "slideshow": {
+     "slide_type": "fragment"
+    },
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "#| export \n",
+    "for i,url in enumerate(urls):\n",
+    "    download_url(url,f\"data/{query}/{query}_{i+1}.jpg\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#| export\n",
+    "import shutil \n",
+    "\n",
+    "shutil.rmtree(f\"data/{query}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# download_url(urls[0], 'images/bear.jpg')\n",
+    "# img = Image.open('images/bear.jpg')\n",
+    "# img.thumbnail((256,256))\n",
+    "# img"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# import os\n",
+    "# rmdir only removes empty directory\n",
+    "# os.rmdir(f\"./{query}\")\n",
+    "# os.listdir(\".\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!nbdev_export"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "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": "3.10.10"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}