updated

app.py

@@ -1,19 +1,23 @@
-from fastai.vision.all import *
 import gradio as gr
+import torch
+import requests
+from torchvision import transforms
 
-def is_cat(x): return x[0].isupper()
-im = PILImage.create('/dog.jpg')
-im.thumbnail((192,192))
-learn =load_learner('/model.pkl')
-categories = ('dog','cat')
+model = torch.hub.load('pytorch/vision:v0.6.0', 'resnet18', pretrained=True).eval()
+response = requests.get("https://git.io/JJkYN")
+labels = response.text.split("\n")
 
-def classify_image(img):
-    pred,idx,probs = learn.predict(img)
-    return dict(zip(categories,map(float,probs)))
+def predict(inp):
+    inp = transforms.ToTensor()(inp).unsqueeze(0)
+    with torch.no_grad():
+        prediction = torch.nn.functional.softmax(model(inp)[0], dim=0)
+        confidences = {labels[i]: float(prediction[i]) for i in range(1000)}
+    return confidences
 
-#gradio interface
-image = gr.inputs.Image(shape=(192,192))
-label=gr.outputs.Label()
-examples=['dog.jpg','cat.jpg','dunno.jpg']
-intf=gr.Interface(fn=classify_image,inputs=image,outputs=label,example=examples)
-intf.launch(inline=False)
+demo = gr.Interface(fn=predict,
+        inputs=gr.inputs.Image(type="pil"),
+        outputs=gr.outputs.Label(num_top_classes=3),
+        examples=[["dog.jpg"]],
+        )
+
+demo.launch()