PyTorch version to screen and cleanup (#1325)

models/yolo.py

 import argparse
 import logging
+import math
 import sys
 from copy import deepcopy
 from pathlib import Path
 
-import math
-
 sys.path.append('./')  # to run '$ python *.py' files in subdirectories
 logger = logging.getLogger(__name__)
 
@@ -74,7 +73,7 @@ class Model(nn.Module):
 
         # Define model
         if nc and nc != self.yaml['nc']:
-            print('Overriding model.yaml nc=%g with nc=%g' % (self.yaml['nc'], nc))
+            logger.info('Overriding model.yaml nc=%g with nc=%g' % (self.yaml['nc'], nc))
             self.yaml['nc'] = nc  # override yaml value
         self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch])  # model, savelist, ch_out
         # print([x.shape for x in self.forward(torch.zeros(1, ch, 64, 64))])
@@ -93,7 +92,7 @@ class Model(nn.Module):
         # Init weights, biases
         initialize_weights(self)
         self.info()
-        print('')
+        logger.info('')
 
     def forward(self, x, augment=False, profile=False):
         if augment:

test.py

@@ -262,6 +262,7 @@ def test(data,
             print('ERROR: pycocotools unable to run: %s' % e)
 
     # Return results
+    if not training:
         print('Results saved to %s' % save_dir)
     model.float()  # for training
     maps = np.zeros(nc) + map

utils/datasets.py

@@ -946,3 +946,11 @@ def create_folder(path='./new'):
     if os.path.exists(path):
         shutil.rmtree(path)  # delete output folder
     os.makedirs(path)  # make new output folder
+
+
+def flatten_recursive(path='../coco128'):
+    # Flatten a recursive directory by bringing all files to top level
+    new_path = Path(path + '_flat')
+    create_folder(new_path)
+    for file in tqdm(glob.glob(str(Path(path)) + '/**/*.*', recursive=True)):
+        shutil.copyfile(file, new_path / Path(file).name)

utils/torch_utils.py

 import logging
+import math
 import os
 import time
 from copy import deepcopy
 
-import math
 import torch
 import torch.backends.cudnn as cudnn
 import torch.nn as nn
@@ -39,14 +39,13 @@ def select_device(device='', batch_size=None):
         if ng > 1 and batch_size:  # check that batch_size is compatible with device_count
             assert batch_size % ng == 0, 'batch-size %g not multiple of GPU count %g' % (batch_size, ng)
         x = [torch.cuda.get_device_properties(i) for i in range(ng)]
-        s = 'Using CUDA '
+        s = f'Using torch {torch.__version__} '
         for i in range(0, ng):
             if i == 1:
                 s = ' ' * len(s)
-            logger.info("%sdevice%g _CudaDeviceProperties(name='%s', total_memory=%dMB)" %
-                        (s, i, x[i].name, x[i].total_memory / c))
+            logger.info("%sCUDA:%g (%s, %dMB)" % (s, i, x[i].name, x[i].total_memory / c))
     else:
-        logger.info('Using CPU')
+        logger.info(f'Using torch {torch.__version__} CPU')
 
     logger.info('')  # skip a line
     return torch.device('cuda:0' if cuda else 'cpu')
@@ -143,7 +142,7 @@ def model_info(model, verbose=False):
         from thop import profile
         flops = profile(deepcopy(model), inputs=(torch.zeros(1, 3, 64, 64),), verbose=False)[0] / 1E9 * 2
         fs = ', %.1f GFLOPS' % (flops * 100)  # 640x640 FLOPS
-    except:
+    except ImportError:
         fs = ''
 
     logger.info(