Create app.py

app.py

@@ -0,0 +1,32 @@
+!pip install gradio
+
+from fastai.vision.all import *
+import gradio as gr
+
+#im1 = PILImage.create('/kaggle/input/flowersdata/balsamroot/02d06c11-5738-47f0-bfaf-af79eb1d4405.jpg')
+#im2 = PILImage.create('/kaggle/input/flowersdata/brittlebrush/ed0dc07f-49b3-48f0-9663-aefee1d3096b.jpg')
+
+learn = load_learner('/kaggle/input/save-your-neural-network-as-a-pkl-file/export.pkl')
+
+pred_class,pred_idx,probabilities = learn.predict(im1)
+pred_class, pred_idx, probabilities
+
+pred_class,pred_idx,probabilities = learn.predict(im2)
+pred_class, pred_idx, probabilities
+
+categories = ('balsamroot', 'bladderpod', 'blazing star', 'bristlecone pine flowers', 'brittlebrush')
+def classify_image(img):
+    pred, idx, probs = learn.predict(img)
+    return dict(zip(categories, map(float, probs)))
+
+
+classify_image(im1), classify_image(im2)
+
+image=gr.Image(height = 192, width = 192)
+label = gr.Label()
+#examples = ['/kaggle/input/example-images/Ronan_Grizzly_Bear_1.jpg','/kaggle/input/example-images/blackbear.jpg',
+            '/kaggle/input/example-images/blackbear2.jpg','/kaggle/input/example-images/brownbear.jpg',
+           '/kaggle/input/example-images/polar.jpg']
+intf = gr.Interface(fn=classify_image, inputs=image, outputs=label, examples=examples)
+intf.launch(inline=False)
+