Update app.py

app.py

@@ -1,12 +1,46 @@
 import gradio as gr 
 import tensorflow as tf
+from keras.models import load_model
+import segmentation_models as sm
+from keras.metrics import MeanIoU
 
+def jaccard_coef(y_true, y_pred):
+    """
+    Defines custom jaccard coefficient metric
+    """
+    
+    y_true_flatten = K.flatten(y_true)
+    y_pred_flatten = K.flatten(y_pred)
+    intersection = K.sum(y_true_flatten * y_pred_flatten)
+    final_coef_value = (intersection + 1.0) / (K.sum(y_true_flatten) + K.sum(y_pred_flatten) - intersection + 1.0)
+    return final_coef_value
 
-def greet(name):
-    return "Hello " + name + "!!"
+def real_dice_coeff(y_true, y_pred):
+    smooth = 0.0001
+    y_true_flatten = K.flatten(y_true)
+    y_pred_flatten = K.flatten(y_pred)
+    intersection = K.sum(y_true_flatten * y_pred_flatten)
+    dice_score = (2.0 * intersection + smooth) / (K.sum(y_true_flatten) + K.sum(y_pred_flatten) + smooth)
+    return dice_score
 
-iface = gr.Interface(fn=greet, inputs="text", outputs="text")
-iface.launch()
+
+dice_loss = sm.losses.DiceLoss(class_weights = weights)
+focal_loss = sm.losses.CategoricalFocalLoss()
+TOTAL_LOSS_FACTOR = 5
+total_loss = dice_loss + (TOTAL_LOSS_FACTOR * focal_loss)
+
+metrics = [real_dice_coeff, tf.keras.metrics.MeanIoU(num_classes=2, sparse_y_true= False, sparse_y_pred=False, name="Mean IOU"), "accuracy", jaccard_coef, sm.metrics.FScore(threshold=0.6, name="Dice Coeficient")]
+
+
+model = load_model('../../../fast-disk/w210-capstone/models/' + model_name, custom_objects={'dice_loss_plus_5focal_loss': total_loss, 'jaccard_coef': jaccard_coef, 'IOU score' : sm.metrics.IOUScore(threshold=0.9, name="IOU score"), 'Dice Coeficient' : sm.metrics.FScore(threshold=0.6, name="Dice Coeficient")}, compile=False)
+model.compile(metrics=metrics)
+
+
+# def greet(name):
+#     return "Hello " + name + "!!"
+
+# iface = gr.Interface(fn=greet, inputs="text", outputs="text")
+# iface.launch()
 
 
 # first we need to load the model from somewhere - probably by using model.load on a keras file (which could be saved in our huggingface space repo)