Update pages/Entorno de Ejecución.py

pages/Entorno de Ejecución.py

@@ -1,7 +1,7 @@
 import streamlit as st
 import tensorflow as tf
 from tensorflow.keras.models import load_model
-from transformers import AutoConfig, AutoModel, pipeline#, AutoProcessor, AutoModelForZeroShotImageClassification
+from transformers import AutoConfig, AutoModel, pipeline, Dinov2Model#, AutoProcessor, AutoModelForZeroShotImageClassification
 from PIL import Image 
 import os
 import torch
@@ -170,7 +170,7 @@ with vit:
             'microsoft/swin-tiny-patch4-window7-224' : 'frncscp/patacoswin'
         }
         
-        model_choice = st.multiselect("Seleccione un modelo de clasificación", model_dict.keys(), key = 'ViT_multiselect')
+        model_choice = st.selectbox("Seleccione un modelo de clasificación", model_dict.keys(), key = 'ViT_select')
         
         uploaded_file = st.file_uploader(key = 'ViT_upload', label = 'Sube la imagen a clasificar',type= ['jpg','png', 'jpeg', 'jfif', 'webp', 'heic'])
         flag = False
@@ -186,7 +186,10 @@ with vit:
 
                     #y_gorritoo = query(uploaded_file.read(), model_dict[model_choice[0]]) 
                     #st.write(y_gorritoo)
-                    classifiers = [pipeline("image-classification", model= model_dict[model_choice[i]]) for i in range(len(model_choice))]
+                    if "frncscp/dinotron" in model_choice.values():
+                        classifiers = [Dinov2Model.from_pretrained("frncscp/dinotron")]
+                    else:
+                        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')