Update app.py

app.py

@@ -1,187 +1,27 @@
-# %% [code] {"execution":{"iopub.status.busy":"2023-01-19T13:44:50.747581Z","iopub.execute_input":"2023-01-19T13:44:50.748868Z","iopub.status.idle":"2023-01-19T13:44:50.788780Z","shell.execute_reply.started":"2023-01-19T13:44:50.748755Z","shell.execute_reply":"2023-01-19T13:44:50.787152Z"},"jupyter":{"source_hidden":true}}
-#NB: Kaggle requires phone verification to use the internet or a GPU. If you haven't done that yet, the cell below will fail
-#    This code is only here to check that your internet is enabled. It doesn't do anything else.
-#    Here's a help thread on getting your phone number verified: https://www.kaggle.com/product-feedback/135367
+# AUTOGENERATED! DO NOT EDIT! File to edit: . (unless otherwise specified).
 
-import socket,warnings
-try:
-    socket.setdefaulttimeout(1)
-    socket.socket(socket.AF_INET, socket.SOCK_STREAM).connect(('1.1.1.1', 53))
-except socket.error as ex: raise Exception("STOP: No internet. Click '>|' in top right and set 'Internet' switch to on")
-
-# %% [code] {"_kg_hide-input":true,"_kg_hide-output":true,"execution":{"iopub.status.busy":"2023-01-19T13:44:55.472652Z","iopub.execute_input":"2023-01-19T13:44:55.473277Z","iopub.status.idle":"2023-01-19T13:45:07.027672Z","shell.execute_reply.started":"2023-01-19T13:44:55.473245Z","shell.execute_reply":"2023-01-19T13:45:07.026513Z"},"jupyter":{"source_hidden":true}}
-# It's a good idea to ensure you're running the latest version of any libraries you need.
-# `!pip install -Uqq <libraries>` upgrades to the latest version of <libraries>
-# NB: You can safely ignore any warnings or errors pip spits out about running as root or incompatibilities
-import os
-iskaggle = os.environ.get('KAGGLE_KERNEL_RUN_TYPE', '')
-
-# %% [markdown]
-# In 2015 the idea of creating a computer system that could recognise birds was considered so outrageously challenging that it was the basis of [this XKCD joke](https://xkcd.com/1425/):
-
-# %% [markdown]
-# ![image.png](attachment:a0483178-c30e-4fdd-b2c2-349e130ab260.png)
-
-# %% [markdown]
-# But today, we can do exactly that, in just a few minutes, using entirely free resources!
-#
-# The basic steps we'll take are:
-#
-# 1. Use DuckDuckGo to search for images of "bird photos"
-# 1. Use DuckDuckGo to search for images of "forest photos"
-# 1. Fine-tune a pretrained neural network to recognise these two groups
-# 1. Try running this model on a picture of a bird and see if it works.
-
-# %% [markdown]
-# ## Step 1: Download images of birds and non-birds
-
-# %% [code] {"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-01-19T13:45:56.061456Z","iopub.execute_input":"2023-01-19T13:45:56.061849Z","iopub.status.idle":"2023-01-19T13:45:56.069190Z","shell.execute_reply.started":"2023-01-19T13:45:56.061817Z","shell.execute_reply":"2023-01-19T13:45:56.067878Z"}}
-from duckduckgo_search import ddg_images
-from fastcore.all import *
-
-def search_images(term, max_images=30):
-    print(f"Searching for '{term}'")
-    return L(ddg_images(term, max_results=max_images)).itemgot('image')
-
-# %% [code] {"execution":{"iopub.status.busy":"2023-01-19T13:45:51.347402Z","iopub.execute_input":"2023-01-19T13:45:51.347810Z","iopub.status.idle":"2023-01-19T13:45:51.408967Z","shell.execute_reply.started":"2023-01-19T13:45:51.347776Z","shell.execute_reply":"2023-01-19T13:45:51.407774Z"}}
-
-
-# %% [markdown]
-# Let's start by searching for a bird photo and seeing what kind of result we get. We'll start by getting URLs from a search:
-
-# %% [code] {"execution":{"iopub.status.busy":"2023-01-19T13:46:01.346523Z","iopub.execute_input":"2023-01-19T13:46:01.347704Z","iopub.status.idle":"2023-01-19T13:46:01.848775Z","shell.execute_reply.started":"2023-01-19T13:46:01.347644Z","shell.execute_reply":"2023-01-19T13:46:01.847667Z"}}
-#NB: `search_images` depends on duckduckgo.com, which doesn't always return correct responses.
-#    If you get a JSON error, just try running it again (it may take a couple of tries).
-urls = search_images('snowboard', max_images=1)
-urls[0]
-
-# %% [markdown]
-# ...and then download a URL and take a look at it:
-
-# %% [code] {"execution":{"iopub.status.busy":"2023-01-19T13:46:15.912826Z","iopub.execute_input":"2023-01-19T13:46:15.913436Z","iopub.status.idle":"2023-01-19T13:46:21.067256Z","shell.execute_reply.started":"2023-01-19T13:46:15.913404Z","shell.execute_reply":"2023-01-19T13:46:21.066186Z"}}
-from fastdownload import download_url
-dest = 'snowboard.jpg'
-download_url(urls[0], dest, show_progress=False)
+__all__ = ['is_cat', 'learn', 'classify_image', 'categories', 'image', 'label', 'examples', 'intf']
 
+# Cell
 from fastai.vision.all import *
-im = Image.open(dest)
-im.to_thumb(256,256)
-
-# %% [markdown]
-# Now let's do the same with "forest photos":
-
-# %% [code] {"execution":{"iopub.status.busy":"2023-01-19T13:46:30.534509Z","iopub.execute_input":"2023-01-19T13:46:30.535405Z","iopub.status.idle":"2023-01-19T13:46:32.663418Z","shell.execute_reply.started":"2023-01-19T13:46:30.535368Z","shell.execute_reply":"2023-01-19T13:46:32.662448Z"}}
-download_url(search_images('snowboard', max_images=1)[0], 'snowboard.jpg', show_progress=False)
-Image.open('snowboard.jpg').to_thumb(256,256)
-
-# %% [markdown]
-# Our searches seem to be giving reasonable results, so let's grab a few examples of each of "bird" and "forest" photos, and save each group of photos to a different folder (I'm also trying to grab a range of lighting conditions here):
-
-# %% [code] {"execution":{"iopub.status.busy":"2023-01-19T13:46:44.584802Z","iopub.execute_input":"2023-01-19T13:46:44.585202Z","iopub.status.idle":"2023-01-19T13:48:11.129905Z","shell.execute_reply.started":"2023-01-19T13:46:44.585170Z","shell.execute_reply":"2023-01-19T13:48:11.128350Z"}}
-searches = 'skis','snowboard'
-path = Path('snowboard_or_not')
-from time import sleep
-
-for o in searches:
-    dest = (path/o)
-    dest.mkdir(exist_ok=True, parents=True)
-    download_images(dest, urls=search_images(f'{o} photo'))
-    sleep(10)  # Pause between searches to avoid over-loading server
-    download_images(dest, urls=search_images(f'{o} backcountry photo'))
-    sleep(10)
-    download_images(dest, urls=search_images(f'{o} downhill photo'))
-    sleep(10)
-    resize_images(path/o, max_size=400, dest=path/o)
-
-# %% [markdown]
-# ## Step 2: Train our model
-
-# %% [markdown]
-# Some photos might not download correctly which could cause our model training to fail, so we'll remove them:
-
-# %% [code] {"execution":{"iopub.status.busy":"2023-01-19T13:48:13.927238Z","iopub.execute_input":"2023-01-19T13:48:13.927600Z","iopub.status.idle":"2023-01-19T13:48:14.375727Z","shell.execute_reply.started":"2023-01-19T13:48:13.927569Z","shell.execute_reply":"2023-01-19T13:48:14.374184Z"}}
-failed = verify_images(get_image_files(path))
-failed.map(Path.unlink)
-len(failed)
-
-# %% [markdown]
-# To train a model, we'll need `DataLoaders`, which is an object that contains a *training set* (the images used to create a model) and a *validation set* (the images used to check the accuracy of a model -- not used during training). In `fastai` we can create that easily using a `DataBlock`, and view sample images from it:
-
-# %% [code] {"execution":{"iopub.status.busy":"2023-01-19T13:48:18.530196Z","iopub.execute_input":"2023-01-19T13:48:18.530595Z","iopub.status.idle":"2023-01-19T13:48:19.133024Z","shell.execute_reply.started":"2023-01-19T13:48:18.530562Z","shell.execute_reply":"2023-01-19T13:48:19.132389Z"}}
-dls = DataBlock(
-    blocks=(ImageBlock, CategoryBlock),
-    get_items=get_image_files,
-    splitter=RandomSplitter(valid_pct=0.2, seed=42),
-    get_y=parent_label,
-    item_tfms=[Resize(192, method='squish')]
-).dataloaders(path, bs=32)
-
-dls.show_batch(max_n=6)
-
-# %% [markdown]
-# Here what each of the `DataBlock` parameters means:
-#
-#     blocks=(ImageBlock, CategoryBlock),
-#
-# The inputs to our model are images, and the outputs are categories (in this case, "bird" or "forest").
-#
-#     get_items=get_image_files,
-#
-# To find all the inputs to our model, run the `get_image_files` function (which returns a list of all image files in a path).
-#
-#     splitter=RandomSplitter(valid_pct=0.2, seed=42),
-#
-# Split the data into training and validation sets randomly, using 20% of the data for the validation set.
-#
-#     get_y=parent_label,
-#
-# The labels (`y` values) is the name of the `parent` of each file (i.e. the name of the folder they're in, which will be *bird* or *forest*).
-#
-#     item_tfms=[Resize(192, method='squish')]
-#
-# Before training, resize each image to 192x192 pixels by "squishing" it (as opposed to cropping it).
-
-# %% [markdown]
-# Now we're ready to train our model. The fastest widely used computer vision model is `resnet18`. You can train this in a few minutes, even on a CPU! (On a GPU, it generally takes under 10 seconds...)
-#
-# `fastai` comes with a helpful `fine_tune()` method which automatically uses best practices for fine tuning a pre-trained model, so we'll use that.
-
-# %% [code] {"execution":{"iopub.status.busy":"2023-01-19T13:48:35.151957Z","iopub.execute_input":"2023-01-19T13:48:35.153822Z","iopub.status.idle":"2023-01-19T13:49:18.382049Z","shell.execute_reply.started":"2023-01-19T13:48:35.153778Z","shell.execute_reply":"2023-01-19T13:49:18.380613Z"}}
-learn = vision_learner(dls, resnet18, metrics=error_rate)
-learn.fine_tune(3)
-
-# %% [markdown]
-# Generally when I run this I see 100% accuracy on the validation set (although it might vary a bit from run to run).
-#
-# "Fine-tuning" a model means that we're starting with a model someone else has trained using some other dataset (called the *pretrained model*), and adjusting the weights a little bit so that the model learns to recognise your particular dataset. In this case, the pretrained model was trained to recognise photos in *imagenet*, and widely-used computer vision dataset with images covering 1000 categories) For details on fine-tuning and why it's important, check out the [free fast.ai course](https://course.fast.ai/).
-
-# %% [markdown]
-# ## Step 3: Use our model (and build your own!)
-
-# %% [markdown]
-# Let's see what our model thinks about that bird we downloaded at the start:
-
-# %% [code] {"execution":{"iopub.status.busy":"2023-01-19T13:50:02.912145Z","iopub.execute_input":"2023-01-19T13:50:02.912475Z","iopub.status.idle":"2023-01-19T13:50:03.010309Z","shell.execute_reply.started":"2023-01-19T13:50:02.912450Z","shell.execute_reply":"2023-01-19T13:50:03.009055Z"}}
-is_snowboard,_,probs = learn.predict(PILImage.create('snowboard.jpg'))
+import gradio as gr
 
-print(dls.vocab)
-print(dls.vocab.o2i)
-print(f"Probability that it is a {is_snowboard}: {probs[dls.vocab.o2i.get(is_snowboard)]:.4f}")
+def is_cat(x): return x[0].isupper()
 
-# %% [code] {"execution":{"iopub.status.busy":"2023-01-19T12:43:17.999435Z","iopub.execute_input":"2023-01-19T12:43:17.999835Z","iopub.status.idle":"2023-01-19T12:43:18.006416Z","shell.execute_reply.started":"2023-01-19T12:43:17.999788Z","shell.execute_reply":"2023-01-19T12:43:18.005077Z"}}
+# Cell
+learn = load_learner('model.pkl')
 
+# Cell
+categories = ('Dog', 'Cat')
 
+def classify_image(img):
+    pred,idx,probs = learn.predict(img)
+    return dict(zip(categories, map(float,probs)))
 
-# %% [markdown]
-# Good job, resnet18. :)
-#
-# So, as you see, in the space of a few years, creating computer vision classification models has gone from "so hard it's a joke" to "trivially easy and free"!
-#
-# It's not just in computer vision. Thanks to deep learning, computers can now do many things which seemed impossible just a few years ago, including [creating amazing artworks](https://openai.com/dall-e-2/), and [explaining jokes](https://www.datanami.com/2022/04/22/googles-massive-new-language-model-can-explain-jokes/). It's moving so fast that even experts in the field have trouble predicting how it's going to impact society in the coming years.
-#
-# One thing is clear -- it's important that we all do our best to understand this technology, because otherwise we'll get left behind!
+# Cell
+image = gr.inputs.Image(shape=(192, 192))
+label = gr.outputs.Label()
+examples = ['dog.jpg', 'cat.jpg', 'dunno.jpg']
 
-# %% [markdown]
-# Now it's your turn. Click "Copy & Edit" and try creating your own image classifier using your own image searches!
-#
-# If you enjoyed this, please consider clicking the "upvote" button in the top-right -- it's very encouraging to us notebook authors to know when people appreciate our work.
+intf = gr.Interface(fn=classify_image, inputs=image, outputs=label, examples=examples)
+intf.launch(inline=False)