Update app.py

app.py

@@ -1,20 +1,15 @@
 import streamlit as st
 import matplotlib.pyplot as plt
-import torchvision
-from torchvision.transforms import ToTensor
-from transformers import ViTModel
-from transformers.modeling_outputs import SequenceClassifierOutput
+
 import torch.nn as nn
-import torch.nn.functional as F
-from transformers import ViTFeatureExtractor
+
 import torch
-import torch.utils.data as data
-from torch.autograd import Variable
+
 import numpy as np
 import os
-import torch.optim as optim
+
 from torchvision.transforms import transforms
-from torch.utils.data import DataLoader
+
 from vit_pytorch import ViT
 from PIL import Image
 
@@ -24,6 +19,7 @@ import math
 from functools import partial
 import torch
 import torch.nn as nn
+
 from PIL import Image
 from torchvision import transforms
 import matplotlib.pyplot as plt
@@ -410,6 +406,7 @@ from functools import partial
 import torch
 import torch.nn as nn
 
+
 import io
 from PIL import Image
 from torchvision import transforms
@@ -594,6 +591,10 @@ except:
         st.sidebar.write(factor_reduce)
 
         return realtime_update,box_color,aspect_ratio,factor_reduce
+
+    
+    
+
     st.title('ระบบวินิฉัยโรคมะเร็งหู')
     st.info('กรุณาถ่ายภาพหูอย่างชัดเจนและควรใช้กล้องคุณภาพสูง เพื่อประสิทธิภาพที่ดีที่สุด', icon="ℹ️")
     img_path = st.camera_input(label="From camera",label_visibility="hidden")
@@ -636,6 +637,7 @@ except:
         _ = cropped_img.thumbnail((224,224))
         st.image(cropped_img)
 
+
     if img_path or img_upload is not None:
         image_path = (cropped_img)  
         result = st.button("วินิฉัย",type="primary",use_container_width=True)
@@ -659,11 +661,23 @@ except:
             img = Image.open(path)
             predicted, threshold = Classification(path)
             print(4*form_score)
-            newthreshold = float(threshold.replace("%","")) - (4*form_score)
-            if predicted != 'Not_EarCancer' and newthreshold > 50:
-                st.markdown(f'<h1 style="color:red;">ชนิดโรค: {predicted} , มั่นใจ: {newthreshold}%</h1>', unsafe_allow_html=True)
+            if predicted != 'Not_EarCancer':
+                newthreshold = float(threshold.replace("%","")) - (4*form_score)
+            else:
+                newthreshold = float(threshold.replace("%",""))
+            if predicted != 'Not_EarCancer':
+                if newthreshold > 50:
+                    if newthreshold >70:
+                        st.markdown(f'<h1 style="color:red;">ชนิดโรค: {predicted} , มั่นใจ: {newthreshold}%</h1>', unsafe_allow_html=True)
+                        st.markdown(f'<h1 style="color:red;">🚨 คุณมีความเสี่ยงเป็น{predicted}สูง โปรดปรึกษาแพทย์!</h1>', unsafe_allow_html=True)
+                    if newthreshold <70:
+                        st.markdown(f'<h1 style="color:orange;">ชนิดโรค: {predicted} , มั่นใจ: {newthreshold}%</h1>', unsafe_allow_html=True)
+                        st.markdown(f'<h1 style="color:orange;">🟡 คุณมีโอกาศเป็น{predicted} โปรดเฝ้าระวัง</h1>', unsafe_allow_html=True)
+                else:
+                    st.markdown(f'<h1 style="color:green;">ชนิดโรค: {predicted} , มั่นใจ: {newthreshold}%</h1>', unsafe_allow_html=True)
+                    st.markdown(f'<h1 style="color:green;">✅ คุณมีโอกาศเป็น{predicted}ต่ำ</h1>', unsafe_allow_html=True)
             else:
-                st.markdown(f'<h1 style="color:green;">หูปกติ ไม่เป็นโรค , มั่นใจ: {newthreshold}%</h1>', unsafe_allow_html=True)
+                st.markdown(f'<h1 style="color:green;">ชนิดโรค: {predicted} , มั่นใจ: {newthreshold}%</h1>', unsafe_allow_html=True)
             img_size = tuple(np.array(img.size[::-1]) // int(factor_reduce))
             model = VitGenerator(name_model, patch_size,device, evaluate=True, random=False, verbose=True)
             visualize_predict(model, img, img_size, patch_size, device)