Update pages/Entorno de Ejecución.py

pages/Entorno de Ejecución.py

@@ -50,8 +50,8 @@ headers = {"Authorization": f"Bearer {st.secrets['token']}"}
 
 def query(data, model_name): #HF API
     response = requests.post(API_URL + "/" + model_name, headers=headers, data=data)
-    while "error" in response.json():
-        with st.spinner("El modelo está cargando, luego hace predicciones rápidas"):
+    with st.spinner("Cargando Predicción... (si se demora un poco, es probable que esté cargando el modelo)"):
+        while "error" in response.json(): 
             response = requests.post(API_URL + "/" + model_name, headers=headers, data=data)
     return response.json() #.json
 
@@ -175,12 +175,11 @@ with vit:
                 with st.spinner('Cargando predicción...'):
 
                     api_result = query(uploaded_file.read(), model_dict[model_choice[0]]) 
-                    st.write(api_result)
 
-                    classifiers = [pipeline("image-classification", model= model_dict[model_choice[i]]) for i in range(len(model_choice))]
+                    #classifiers = [pipeline("image-classification", model= model_dict[model_choice[i]]) for i in range(len(model_choice))]
                     
                     #classifier = pipeline("image-classification", model= model_dict[model_choice[0]])
-                    img = preprocess(uploaded_file, module = 'pil')
+                    #img = preprocess(uploaded_file, module = 'pil')
 
 
                     def vit_ensemble(classifier_list, img):
@@ -191,7 +190,15 @@ with vit:
                                 if clase['label'] == 'Patacon-True':
                                     y_gorrito += clase["score"]
                         return y_gorrito / len(classifier_list)
+
+
+                    y_gorrito = 0
                     
+                    for model in model_choice:
+                        api_result = query(uploaded_file.read(), model_dict[model]) 
+                        y_gorrito += api_result[1]["score"]                   
+                    y_gorrito /= len(model_choice)
+                        
                     #classifier = classifier(img) 
 
                     #for clase in classifier:
@@ -201,7 +208,7 @@ with vit:
                 #y_gorrito = classifier[0]["score"]
                     
                     
-                    y_gorrito = vit_ensemble(classifiers, img)
+                    #y_gorrito = vit_ensemble(classifiers, img)
                     
                     if round(float(y_gorrito*100)) >= threshold:
                         st.success("¡Patacón Detectado!")