add os.path.join

get_json_file_YOLO.py

@@ -5,10 +5,16 @@ import labelme
 import base64
 import pandas as pd
 
+def arg_directory(path):
+    if os.path.isdir(path):
+        return path
+    else:
+        raise argparse.ArgumentTypeError(f'`{path}` is not a valid path')
+
 parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter, description='TODO')
-parser.add_argument('-p','--path_to_json', type=str, help = 'Path of the folder that contain the .json',required=True)
-parser.add_argument('-i','--path_to_img', type=str, help = 'Path of the folder that contain the .jpg',required=True)
-parser.add_argument('-d','--direction', type=str, help = 'Directory to wich modified .json files will be stored',required=True)
+parser.add_argument('-p','--path_to_json', type=arg_directory, help = 'Path of the folder that contain the .json',required=True)
+parser.add_argument('-i','--path_to_img', type=arg_directory, help = 'Path of the folder that contain the .jpg',required=True)
+parser.add_argument('-d','--direction', type=arg_directory, help = 'Directory to wich modified .json files will be stored',required=True)
 args = parser.parse_args()
 
 
@@ -27,7 +33,7 @@ liste_file = liste_file.reset_index()
 
 for i, row in liste_file.iterrows():
     if len(row.fn) > 30:
-        data = labelme.LabelFile.load_image_file(str(img_path+row.fn[:-4]+'jpg'))
+        data = labelme.LabelFile.load_image_file(os.path.join(img_path,str(row.fn[:-4]+'jpg')))
         image_data = base64.b64encode(data).decode('utf-8')
     else:
         continue

get_spectrogram.py

@@ -10,10 +10,16 @@ from p_tqdm import p_map
 import warnings
 warnings.filterwarnings('ignore')
 
+def arg_directory(path):
+    if os.path.isdir(path):
+        return path
+    else:
+        raise argparse.ArgumentTypeError(f'`{path}` is not a valid path')
+
 parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter, description='TODO')
 parser.add_argument('-f','--file', type=str,required=True,help = 'Name of the file that contain the recording to print')
-parser.add_argument('-p','--path_to_data', type=str, help = 'Path of the folder that contain the recordings',required=True)
-parser.add_argument('-d','--direction', type=str, help = 'Directory to wich spectrogram will be stored',required=True)
+parser.add_argument('-p','--path_to_data', type=arg_directory, help = 'Path of the folder that contain the recordings',required=True)
+parser.add_argument('-d','--direction', type=arg_directory, help = 'Directory to wich spectrogram will be stored',required=True)
 parser.add_argument('-m','--mode', type=str,choices=['unique','multiple'], help = 'Direction of the saved spectrogram',required=True)
 args = parser.parse_args()
 
@@ -29,7 +35,7 @@ elif args.mode == 'unique':
     NB_IMG_PER_REC = 1
 
 
-df = pd.read_csv(str(args.file),low_memory=False)
+df = pd.read_csv(args.file,low_memory=False)
 df['Path'] = ''
 #for w in range (len(df)):
 #    df.loc[w,'Path']=str(args.path_to_data+ df.code_unique[w]+"_split_" + str(df.chunk_initial_time[w]) + "_" + str(df.chunk_final_time[w]))
@@ -65,12 +71,12 @@ def process(x):
 
         name = str(i[0].replace('/','_').split('.')[0]+'_'+str(count))
         try :
-            plt.savefig(str(direction+folder+name+'.jpg'))
+            plt.savefig(os.path.join(direction,folder, str(name+'.jpg')))
 
         except FileNotFoundError:
 
-            os.mkdir(str(direction+folder))
-            plt.savefig(str(direction+folder+name+'.jpg'))
+            os.mkdir(os.path.join(direction,folder))
+            plt.savefig(os.path.join(direction,folder, str(name+'.jpg')))
         
 
 p_map(process, enumerate(df.groupby('Path')), num_cpus=10) #la colonne dir correspond au path

get_train_annot_YOLO.py

@@ -12,14 +12,19 @@ import matplotlib.patches as patches
 from matplotlib.patches import Rectangle
 from PIL import Image
 from mycolorpy import colorlist as mcp
-import yaml
 
 today = date.today()
 
+def arg_directory(path):
+    if os.path.isdir(path):
+        return path
+    else:
+        raise argparse.ArgumentTypeError(f'`{path}` is not a valid path')
+
 parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter, description='TODO')
-parser.add_argument('-f','--filename_path', type=str, help = 'Path and name of the file containing the annotations',required=True)
-parser.add_argument('-p','--path_to_data', type=str, help = 'Path of the folder that contain the recordings',required=True)
-parser.add_argument('-d','--direction', type=str, help = 'Directory to wich spectrograms and .txt files will be stored',required=True)
+parser.add_argument('-f','--filename_path', type=arg_directory, help = 'Path and name of the file containing the annotations',required=True)
+parser.add_argument('-p','--path_to_data', type=arg_directory, help = 'Path of the folder that contain the recordings',required=True)
+parser.add_argument('-d','--direction', type=arg_directory, help = 'Directory to wich spectrograms and .txt files will be stored',required=True)
 parser.add_argument('-m','--mode',type=str,choices=['uniform','personalized'],help = 'Choose the mode to calculate the y and height value',required=True)
 parser.add_argument('--export',type=str, default=None, help='To export the position of the bounding box on the spectrogram',required=False)
 args = parser.parse_args()
@@ -74,7 +79,6 @@ color = mcp.gen_color(cmap = "Wistia", n= len(list_espece))
 def process(x):
     count, (f, grp) = x
     filename = str(f)
-    # tqdm.write(filename)
     duration = DURATION
     
     while len(grp) != 0:
@@ -130,32 +134,30 @@ def process(x):
                 elif height_pxl > y_pxl*2:
                     y_pxl=y_pxl+0.5*(height_pxl-y_pxl*2)
 
-
             annotation = pd.DataFrame([[str(data.loc[data.espece == row.Code,'ind'][0]),x_pxl,y_pxl,width_pxl,height_pxl]],columns = ['id','x', 'y', 'width', 'height'])
 
             fin = pd.concat([fin,annotation])
         grp = grp.drop(tab.index)
 
         name = str(row.Path.replace('/','_').replace('.','_')+'_'+str(count))
-        name_file = str(direction+'labels_'+str(today.day)+'_'+str(today.month)+'/'+name+'.txt')
+        name_file = os.path.join(direction,str('labels_'+str(today.day)+'_'+str(today.month)),str(name+'.txt'))
         
         try :
-            plt.savefig(str(direction+"images_"+str(today.day)+'_'+str(today.month)+'/'+row.Code+"/"+name+'.jpg'))
+            plt.savefig(os.path.join(direction,str('images_'+str(today.day)+'_'+str(today.month)),row.Code,str(name+'.jpg')))
             fin.to_csv(name_file,sep =' ',header=False,index=False)
-
-            plt.savefig(str(direction+"images_"+str(today.day)+'_'+str(today.month)+'/'+"all"+"/"+name+'.jpg'))
+            plt.savefig(os.path.join(direction,str('images_'+str(today.day)+'_'+str(today.month)),'all',str(name+'.jpg')))
 
         except :
-            os.mkdir(str(direction+"images_"+str(today.day)+'_'+str(today.month)+'/'))
+            os.mkdir(os.path.join(direction,str('images_'+str(today.day)+'_'+str(today.month))))
             for especes in list_espece.index:
-                os.mkdir(str(direction+"images_"+str(today.day)+'_'+str(today.month)+'/'+especes))
-            os.mkdir(str(direction+"images_"+str(today.day)+'_'+str(today.month)+'/'+'all/'))
 
-            os.mkdir(str(direction+'labels_'+str(today.day)+'_'+str(today.month)+'/'))
+                os.mkdir(os.path.join(direction,str('images_'+str(today.day)+'_'+str(today.month)),especes))
+            os.mkdir(os.path.join(direction,str('images_'+str(today.day)+'_'+str(today.month)),'all'))
+            os.mkdir(os.path.join(direction,str('labels_'+str(today.day)+'_'+str(today.month))))
 
             fin.to_csv(name_file,sep =' ',header=False,index=False)
-            plt.savefig(str(direction+"images_"+str(today.day)+'_'+str(today.month)+'/'+row.Code+"/"+name+'.jpg'))
-            plt.savefig(str(direction+"images_"+str(today.day)+'_'+str(today.month)+'/'+"all"+"/"+name+'.jpg'))
+            plt.savefig(os.path.join(direction,str('images_'+str(today.day)+'_'+str(today.month)),row.Code,str(name+'.jpg')))
+            plt.savefig(os.path.join(direction,str('images_'+str(today.day)+'_'+str(today.month)),'all',str(name+'.jpg')))
 
         if args.export != None:
             for l in range(len(fin)):
@@ -168,11 +170,14 @@ def process(x):
                 except IndexError:
                     ipdb.set_trace()
                 try:
-                    plt.savefig(str(direction+"images_annotes_"+str(today.day)+'_'+str(today.month)+'/'+name+'.jpg'))
+                    plt.savefig(os.path.join, str('images_annotes_'+str(today.day)+'_'+str(today.month)),str(name+'.jpg'))
+
                 except Exception:
-                    os.mkdir(str(direction+"images_annotes_"+str(today.day)+'_'+str(today.month)+'/'))
-                    plt.savefig(str(direction+"images_annotes_"+str(today.day)+'_'+str(today.month)+'/'+name+'.jpg'))
+                    os.mkdir(os.path.join(direction,str('images_annotes_'+str(today.day)+'_'+str(today.month))))
+                    plt.savefig(os.path.join(direction, str('images_annotes_'+str(today.day)+'_'+str(today.month)),str(name+'.jpg')))
 
         plt.close()
 
 p_map(process, enumerate(df.groupby('Path')), num_cpus=10)
+
+print('saved to ',direction)
\ No newline at end of file

get_train_val_YOLO.py

@@ -7,14 +7,20 @@ import shutil
 import argparse
 import ipdb
 
+def arg_directory(path):
+    if os.path.isdir(path):
+        return path
+    else:
+        raise argparse.ArgumentTypeError(f'`{path}` is not a valid path')
+
 parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter, description='TODO')
 parser.add_argument('-r','--ratio', type=float, default = 0.7,help = 'Train Ratio (val = 1 - ratio)')
-parser.add_argument('-p','--path_to_data', type=str, help = 'Path of the folder that contain the .txt (ending with labels/)',required=True)
-parser.add_argument('-d','--direction', type=str, help = 'Directory to wich spectrogram and .txt files will be stored (different from -p)',required=True)
+parser.add_argument('-p','--path_to_data', type=arg_directory, help = 'Path of the folder that contain the .txt (ending with labels/)',required=True)
+parser.add_argument('-d','--direction', type=arg_directory, help = 'Directory to wich spectrogram and .txt files will be stored (different from -p)',required=True)
 args = parser.parse_args()
 
-path = str(args.path_to_data)
-direction = str(args.direction)
+path = args.path_to_data
+direction = args.direction
 NB_CLASS = 50
 
 
@@ -88,25 +94,25 @@ for i in range (len(val)):
 for i in range (len(train)):
     train.file.iloc[i] = train.file.iloc[i][:-4]
 
-isExist = os.path.exists(str(direction+'images'))
+isExist = os.path.exists(os.path.join(direction,'images'))
 
 if not isExist:
-	os.mkdir(str(direction+'images'))
-	os.mkdir(str(direction+'images/train'))
-	os.mkdir(str(direction+'images/val'))
-	os.mkdir(str(direction+'labels'))
-	os.mkdir(str(direction+'labels/train'))
-	os.mkdir(str(direction+'labels/val'))
+	os.mkdir(os.path.join(direction,'images'))
+	os.mkdir(os.path.join(direction,'images/train'))
+	os.mkdir(os.path.join(direction,'images/val'))
+	os.mkdir(os.path.join(direction,'labels'))
+	os.mkdir(os.path.join(direction,'labels/train'))
+	os.mkdir(os.path.join(direction,'labels/val'))
 
 for i,row in tqdm(val.iterrows(), total=val.shape[0]):
 
-	shutil.copy2(str(path+row.file+'.txt'),str(direction+'labels/val/'+row.file+'.txt'))
-	shutil.copy2(str(path+'../images/all/'+row.file+'.jpg'),str(direction+'images/val/'+row.file+'.jpg'))
+	shutil.copy2(os.path.join(path, str(row.file+'.txt')), os.path.join(direction, str('labels/val/'+row.file+'.txt')))
+	shutil.copy2(os.path.join(path, str('../images/all/'+row.file+'.jpg')), os.path.join(direction, str('images/val/'+row.file+'.jpg')))
 
 for i,row in tqdm(train.iterrows(), total=train.shape[0]):
 
-	shutil.copy2(str(path+row.file+'.txt'),str(direction+'labels/train/'+row.file+'.txt'))
-	shutil.copy2(str(path+'../images/all/'+row.file+'.jpg'),str(direction+'images/train/'+row.file+'.jpg'))
+	shutil.copy2(os.path.join(path, str(row.file+'.txt')), os.path.join(direction, str('labels/train/'+row.file+'.txt')))
+	shutil.copy2(os.path.join(path, str('../images/all/'+row.file+'.jpg')), os.path.join(direction, str('images/train/'+row.file+'.jpg')))
 
 liste_espece = pd.read_csv(str(path+'../liste_especes.csv'))
 

get_yolo_detection.py

@@ -5,17 +5,23 @@ from tqdm import tqdm
 import argparse
 from datetime import date
 
+def arg_directory(path):
+    if os.path.isdir(path):
+        return path
+    else:
+        raise argparse.ArgumentTypeError(f'`{path}` is not a valid path')
+
 parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter, description='TODO')
-parser.add_argument('-p','--path_to_data', type=str, help = 'Path of the folder that contain the .txt files',required=True)
-parser.add_argument('-d','--direction', type=str, help = 'Directory to wich the dataframe will be stored',required=True)
+parser.add_argument('-p','--path_to_data', type=arg_directory, help = 'Path of the folder that contain the .txt files',required=True)
+parser.add_argument('-d','--direction', type=arg_directory, help = 'Directory to wich the dataframe will be stored',required=True)
 args = parser.parse_args()
 
-annots = str(args.path_to_data)
+annots = args.path_to_data
 
 today = date.today()
 out_file = str('YOLO_detection_'+str('_'+today.day+'_'+today.month))
 
-outdir = str(args.direction)
+outdir = args.direction
 
 df = pd.DataFrame(columns = ['file','idx','espece','x','y','w','h','conf'])
 for i in tqdm(os.listdir(annots)):
@@ -82,4 +88,4 @@ df['annot'] = 'None'
 for j in range (len(df)):
 	df['annot'].iloc[j] = names[int(df.espece.iloc[j])]
 
-df.to_csv(str(outdir+out_file+'.csv'), index= False)
+df.to_csv(os.path.join(outdir,str(out_file+'.csv')), index= False)