mammal or bird or fish classifier

app.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 40,
    "id": "b0b5e6d7",
    "metadata": {},
    "outputs": [],
@@ -12,21 +12,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 41,
    "id": "894a6707",
    "metadata": {},
    "outputs": [],
    "source": [
     "#|export\n",
-    "!pip install fastai\n",
-    "!pip install gradio\n",
     "from fastai.vision.all import *\n",
     "import gradio as gr"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 42,
    "id": "3308043c",
    "metadata": {},
    "outputs": [],
@@ -37,14 +35,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 47,
    "id": "d9019a15",
    "metadata": {},
    "outputs": [],
    "source": [
     "#|export \n",
     "\n",
-    "categories = ('ocean', 'space', 'money')\n",
+    "categories = ('bird.jpg', 'fish.jpg', 'mammal.jpg')\n",
     "\n",
     "def classify_image(img):\n",
     "    pred, idx, probs = learn.predict(img)\n",
@@ -53,7 +51,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 50,
    "id": "d04d8882",
    "metadata": {},
    "outputs": [
@@ -97,24 +95,24 @@
     {
      "data": {
       "text/plain": [
-       "{'ocean': 5.39313214176218e-06,\n",
-       " 'space': 0.9999582767486572,\n",
-       " 'money': 3.6335437471279874e-05}"
+       "{'bird.jpg': 1.5930112567730248e-05,\n",
+       " 'fish.jpg': 0.9999780654907227,\n",
+       " 'mammal.jpg': 5.961885563010583e-06}"
       ]
      },
-     "execution_count": 6,
+     "execution_count": 50,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "im = PILImage.create('ocean.jpg')\n",
+    "im = PILImage.create('fish.jpg')\n",
     "classify_image(im)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 51,
    "id": "bbef2af6",
    "metadata": {},
    "outputs": [
@@ -136,7 +134,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Running on local URL:  http://127.0.0.1:7860\n",
+      "Running on local URL:  http://127.0.0.1:7863\n",
       "\n",
       "To create a public link, set `share=True` in `launch()`.\n"
      ]
@@ -145,7 +143,7 @@
      "data": {
       "text/plain": []
      },
-     "execution_count": 10,
+     "execution_count": 51,
      "metadata": {},
      "output_type": "execute_result"
     },
@@ -265,7 +263,7 @@
     "#|export\n",
     "image = gr.inputs.Image(shape=(192,192))\n",
     "label = gr.outputs.Label()\n",
-    "examples = ['ocean.jpg', 'space.jpg', 'money.jpg']\n",
+    "examples = ['bird.jpg', 'fish.jpg', 'mammal.jpg']\n",
     "\n",
     "intf = gr.Interface(fn=classify_image, inputs=image, outputs=label, examples=examples)\n",
     "intf.launch(inline=False)"
@@ -273,7 +271,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 52,
    "id": "c0c533db",
    "metadata": {},
    "outputs": [],

app.py

@@ -11,7 +11,7 @@ import gradio as gr
 learn = load_learner('model.pk1')
 
 # %% ../app.ipynb 3
-categories = ('ocean', 'space', 'money')
+categories = ('bird.jpg', 'fish.jpg', 'mammal.jpg')
 
 def classify_image(img):
     pred, idx, probs = learn.predict(img)
@@ -20,7 +20,7 @@ def classify_image(img):
 # %% ../app.ipynb 5
 image = gr.inputs.Image(shape=(192,192))
 label = gr.outputs.Label()
-examples = ['ocean.jpg', 'space.jpg', 'money.jpg']
+examples = ['bird.jpg', 'fish.jpg', 'mammal.jpg']
 
 intf = gr.Interface(fn=classify_image, inputs=image, outputs=label, examples=examples)
 intf.launch(inline=False)

app/app.py

@@ -1,26 +0,0 @@
-# AUTOGENERATED! DO NOT EDIT! File to edit: ../app.ipynb.
-
-# %% auto 0
-__all__ = ['learn', 'categories', 'image', 'label', 'examples', 'intf', 'classify_image']
-
-# %% ../app.ipynb 1
-from fastai.vision.all import *
-import gradio as gr
-
-# %% ../app.ipynb 2
-learn = load_learner('model.pk1')
-
-# %% ../app.ipynb 3
-categories = ('ocean', 'space', 'money')
-
-def classify_image(img):
-    pred, idx, probs = learn.predict(img)
-    return dict(zip(categories, map(float, probs)))
-
-# %% ../app.ipynb 5
-image = gr.inputs.Image(shape=(192,192))
-label = gr.outputs.Label()
-examples = ['ocean.jpg', 'space.jpg', 'money.jpg']
-
-intf = gr.Interface(fn=classify_image, inputs=image, outputs=label, examples=examples)
-intf.launch(inline=False)

model.pk1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c397fb6984c96890e13718ebd9f62f19553c56b7f2cdd6b5d861b7df89461a0c
-size 46958063
+oid sha256:29d1fbdb578b1861ffadbfbafcb4a5c5028f1cf62a6d5445a02c7fe2f626e629
+size 46958891