Update label.py

label.py

@@ -98,34 +98,30 @@ def load_model():
         model._modules.get(name).register_forward_hook(hook_feature)
     return model
 
+# load the labels
+classes, labels_IO, labels_attribute, W_attribute = load_labels()
+
+# load the model
+features_blobs = []
+model = load_model()
 
-def predict_environment(img):
-    # load the labels
-    classes, labels_IO, labels_attribute, W_attribute = load_labels()
-    
-    # load the model
-    features_blobs = []
-    model = load_model()
-    
-    # load the transformer
-    tf = returnTF() # image transformer
 
-    # get the softmax weight
-    params = list(model.parameters())
-    weight_softmax = params[-2].data.numpy()
-    weight_softmax[weight_softmax<0] = 0
+# load the transformer
+tf = returnTF() # image transformer
 
-    #img = Image.open(image)
+# get the softmax weight
+params = list(model.parameters())
+weight_softmax = params[-2].data.numpy()
+weight_softmax[weight_softmax<0] = 0
+
+def predict(img):
+    img = Image.open('6.jpg')
     input_img = V(tf(img).unsqueeze(0))
-    
-    # forward pass
     logit = model.forward(input_img)
     h_x = F.softmax(logit, 1).data.squeeze()
     probs, idx = h_x.sort(0, True)
     probs = probs.numpy()
     idx = idx.numpy()
-    
-    # output the IO prediction
     io_image = np.mean(labels_IO[idx[:10]]) # vote for the indoor or outdoor
     env_image = []
     if io_image < 0.5: