Update pages/Entorno de Ejecución.py

pages/Entorno de Ejecución.py

@@ -32,24 +32,36 @@ classic_ml_root = "/home/user/app/classicML"
 def load_pca():
     return joblib.load(os.path.join(classic_ml_root, "pca_model.pkl"))
 
-def _predict(_model_list, _weights, _img): 
+def _predict(_model_list, _img, sklearn = False): 
     y_gorrito = 0
     raw_img = cv2.cvtColor(_img, cv2.COLOR_BGR2RGB)
     img = cv2.resize(_img, (IMAGE_WIDTH, IMAGE_HEIGHT))
-    for model, weight in zip(_model_list, _weights):
-        y_gorrito += tf.cast(model(tf.expand_dims(img/255., 0)), dtype=tf.float32)*weight
-    return [y_gorrito / sum(_weights), raw_img]
 
-def _pca_predict(models, _img):
-    y_gorrito = 0
-    raw_img = cv2.cvtColor(_img, cv2.COLOR_BGR2RGB)
-    img = cv2.resize(_img, (IMAGE_WIDTH, IMAGE_HEIGHT))
-    fl_img =[img.flatten()]
-    data = pca.transform(fl_img)
-    for model in models:
-        prediction = model.predict_proba(data)
-        y_gorrito += prediction[0][Categories.index("Patacon-True")]
-    return [y_gorrito / len(models), raw_img]
+    if sklearn:
+        fl_img =[img.flatten()]
+        data = pca.transform(fl_img)
+        for model in _model_list:
+            prediction = model.predict_proba(data)
+            y_gorrito += prediction[0][Categories.index("Patacon-True")]
+
+    else:    
+        for model in _model_list:
+            y_gorrito += tf.cast(model(tf.expand_dims(img/255., 0)), dtype=tf.float32)*weight
+    
+    return [y_gorrito / len(_model_list), raw_img]
+
+
+#def _pca_predict(models, _img):
+#    y_gorrito = 0
+#    raw_img = cv2.cvtColor(_img, cv2.COLOR_BGR2RGB)
+#    img = cv2.resize(_img, (IMAGE_WIDTH, IMAGE_HEIGHT))
+#    fl_img =[img.flatten()]
+#    data = pca.transform(fl_img)
+#    for model in models:
+#        prediction = model.predict_proba(data)
+#        y_gorrito += prediction[0][Categories.index("Patacon-True")]
+#    return [y_gorrito / len(models), raw_img]
+
 
 #def classic_ml_prediction(clfs, _img):
 #    y_gorrito = 0
@@ -328,7 +340,7 @@ with classic_ml:
 
                     img = preprocess(uploaded_file)
                     selected_models = [joblib.load(model_dict[model_name]) for model_name in model_choice]
-                    y_gorrito, raw_img =  _pca_predict(selected_models, img)
+                    y_gorrito, raw_img =  _predict(selected_models, img, sklearn = True)
                     
                     if round(float(y_gorrito*100)) >= threshold:
                         st.success("¡Patacón Detectado!")