Update app.py

app.py

@@ -139,89 +139,105 @@ def delete_files_in_folder(path):
 import subprocess
 
 def Aspergillus_Detect():
-  delete_files_in_folder(image_path)
-  # !python detect.py --source Fu-Chuen/Fungus_Classification_Genus_Species/tree/main/Test/ --weights $WEIGHTS --conf 0.25 --save-txt --exist-ok
-  # Construct the command to run the detect.py script
-  command = [
-      "python",
-      "yolov7_environment_data/yolov7/detect.py",
-      "--source",
-      test_path,
-      "--weights",
-      "$WEIGHTS"
-      "--conf",
-      "0.25",
-      "--save-txt",
-      "--exist-ok"
-  ]
-
-  # Run the command as a subprocess
-  process = subprocess.Popen(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
-  stdout, stderr = process.communicate()
-
-  # Print the output and errors if any
-  print("Output:", stdout)
-  print("Errors:", stderr)
-
-  file_paths = []
-  for root, dirs, files in os.walk(label_path):
+    delete_files_in_folder(image_path)
+    # # !python detect.py --source Fu-Chuen/Fungus_Classification_Genus_Species/tree/main/Test/ --weights $WEIGHTS --conf 0.25 --save-txt --exist-ok
+    # # Construct the command to run the detect.py script
+    # command = [
+    #     "python",
+    #     "yolov7_environment_data/yolov7/detect.py",
+    #     "--source",
+    #     test_path,
+    #     "--weights",
+    #     "$WEIGHTS"
+    #     "--conf",
+    #     "0.25",
+    #     "--save-txt",
+    #     "--exist-ok"
+    # ]
+    
+    # # Run the command as a subprocess
+    # process = subprocess.Popen(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+    # stdout, stderr = process.communicate()
+    
+    # # Print the output and errors if any
+    # print("Output:", stdout)
+    # print("Errors:", stderr)
+    
+    
+    !pip install transformers
+    
+    from transformers import AutoModelForYOLO
+    
+    # 在Hugging Face Hub上选择并加载已经训练好的YOLO v7模型
+    model_name = r'Model/best_Yolo_v7.pt'  # 请将"your_yolo_v7_model_name"替换为实际的模型名称
+    model = AutoModelForYOLO.from_pretrained(model_name)
+    
+    # 在此处添加推理代码，根据模型的要求对输入数据进行推理
+    inference_results = model.inference(input_data)
+    print(inference_results)
+    
+    
+    
+    
+    file_paths = []
+    for root, dirs, files in os.walk(label_path):
       for file in files:
           if file.lower().endswith('.jpg'):
               file_path = os.path.join(root, file)
               file_paths.append(file_path)
-
-  df_test = pd.DataFrame({'filepath': file_paths})
-
-  files = os.listdir(label_path)
-
-  # initialize an empty list to store data
-  data = []
-
-  # loop through each file and extract the data
-  for file in files:
+    
+    df_test = pd.DataFrame({'filepath': file_paths})
+    
+    files = os.listdir(label_path)
+    
+    # initialize an empty list to store data
+    data = []
+    
+    # loop through each file and extract the data
+    for file in files:
       if file.endswith('.txt'):
           with open(os.path.join(label_path, file), 'r') as f:
               lines = f.readlines()
               for line in lines:
                   line = line.strip().split(' ')
                   data.append([file[:-4], line[0], float(line[1]), float(line[2]), float(line[3]), float(line[4])])
-
-  # convert list of data to data frame
-  df = pd.DataFrame(data, columns=['image', 'class', 'xmin', 'ymin', 'xmax', 'ymax'])
-  # group by labels, count the number of detections for each label
-  counts = df.groupby(['image', 'class']).size().reset_index(name='count')
-  # add the file name to the data frame
-  counts['file'] = counts['image'].apply(lambda x: x + '.jpg')
-
-  counts['filepath'] = counts['file'].apply(lambda x: Path(label_path,x))
-
-  replace_dict = {'0': 'flavus-oryzae', '1': 'fumigatus', '2': 'niger', '3': 'terreus', '4': 'versicolor'}
-  counts['label'] = counts['class'].replace(replace_dict)
-
-  # Select only the relevant columns
-  counts = counts[['filepath', 'label', 'count']]
-  df_pivot = pd.pivot_table(counts, values='count', index=['filepath'], columns='label', aggfunc='sum')
-  df_pivot['detect'] = df_pivot.sum(axis=1)
-  pd.options.display.float_format = '{:,.0f}'.format
-  df_pivot = pd.DataFrame(df_pivot)
-
-  total_col = df_pivot.pop('detect')
-  df_pivot.insert(0, 'detect', total_col)
-  detect_number = round(df_pivot['detect'].sum())
-  a = []
-  for i in df_pivot.columns[1:]:
+    
+    # convert list of data to data frame
+    df = pd.DataFrame(data, columns=['image', 'class', 'xmin', 'ymin', 'xmax', 'ymax'])
+    # group by labels, count the number of detections for each label
+    counts = df.groupby(['image', 'class']).size().reset_index(name='count')
+    # add the file name to the data frame
+    counts['file'] = counts['image'].apply(lambda x: x + '.jpg')
+    
+    counts['filepath'] = counts['file'].apply(lambda x: Path(label_path,x))
+    
+    replace_dict = {'0': 'flavus-oryzae', '1': 'fumigatus', '2': 'niger', '3': 'terreus', '4': 'versicolor'}
+    counts['label'] = counts['class'].replace(replace_dict)
+    
+    # Select only the relevant columns
+    counts = counts[['filepath', 'label', 'count']]
+    df_pivot = pd.pivot_table(counts, values='count', index=['filepath'], columns='label', aggfunc='sum')
+    df_pivot['detect'] = df_pivot.sum(axis=1)
+    pd.options.display.float_format = '{:,.0f}'.format
+    df_pivot = pd.DataFrame(df_pivot)
+    
+    total_col = df_pivot.pop('detect')
+    df_pivot.insert(0, 'detect', total_col)
+    detect_number = round(df_pivot['detect'].sum())
+    a = []
+    for i in df_pivot.columns[1:]:
     a.append([i,round(df_pivot[i].sum()/detect_number,3)])
-  a = sorted(a,key=lambda x: x[1],reverse=True)
-
-  result = [f'Prediction of species of Aspergillus: {a[0][0] if a[0][1] >= threshold else "Unclassified"}',
+    a = sorted(a,key=lambda x: x[1],reverse=True)
+    
+    result = [f'Prediction of species of Aspergillus: {a[0][0] if a[0][1] >= threshold else "Unclassified"}',
       f'There are {df_pivot.shape[0]} mold images.',
             f'Yolov7 detects {detect_number} instances.',
             f'The top {len(a)} percentage of specifies:']
-  for i in a:
+    for i in a:
     # print(f'i: {i}')
     result.append(f'{i[0]} {i[1]}')
-
-  return '\n'.join(result)
+    
+    return '\n'.join(result)
 
 """# classify images: genus and Aspergillus"""