torchvision

app.py

@@ -3,21 +3,23 @@ import gradio as gr
 
 import torch
 
-model = torch.hub.load('pytorch/vision:v0.6.0', 'resnet18', pretrained=True).eval()
+model = torch.load('v4-epoch=19-val_loss=0.6964-val_accuracy=0.8964.ckpt')
 
 import requests
 from PIL import Image
 from torchvision import transforms
 
 # Download human-readable labels for ImageNet.
-response = requests.get("https://git.io/JJkYN")
-labels = response.text.split("\n")
+labels = ['good', 'ill']
 
 def predict(inp):
-  inp = transforms.ToTensor()(inp).unsqueeze(0)
+  img = transforms.ToTensor()(inp)
+  img = torchvision.transforms.Resize((800, 800))(img)
+  img = torchvision.transforms.CenterCrop(CROP)(img)
+  img = img..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)}    
+    prediction = torch.nn.functional.softmax(model(img)[0], dim=0)
+    confidences = {labels[i]: float(prediction[i]) for i in range(2)}    
   return confidences
 
 import gradio as gr

requirements.txt

@@ -1 +1,2 @@
 torch
+torchvision