remove NBSP

models/yolo.py

@@ -127,7 +127,7 @@ class Model(nn.Module):
     def _initialize_biases(self, cf=None):  # initialize biases into Detect(), cf is class frequency
         # cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1.
         m = self.model[-1]  # Detect() module
-        for mi, s in zip(m.m, m.stride):  #  from
+        for mi, s in zip(m.m, m.stride):  # from
             b = mi.bias.view(m.na, -1)  # conv.bias(255) to (3,85)
             b[:, 4] += math.log(8 / (640 / s) ** 2)  # obj (8 objects per 640 image)
             b[:, 5:] += math.log(0.6 / (m.nc - 0.99)) if cf is None else torch.log(cf / cf.sum())  # cls
@@ -135,7 +135,7 @@ class Model(nn.Module):
 
     def _print_biases(self):
         m = self.model[-1]  # Detect() module
-        for mi in m.m:  #  from
+        for mi in m.m:  # from
             b = mi.bias.detach().view(m.na, -1).T  # conv.bias(255) to (3,85)
             print(('%6g Conv2d.bias:' + '%10.3g' * 6) % (mi.weight.shape[1], *b[:5].mean(1).tolist(), b[5:].mean()))
 

utils/utils.py

@@ -21,7 +21,7 @@ import yaml
 from scipy.signal import butter, filtfilt
 from tqdm import tqdm
 
-from . import torch_utils  #  torch_utils, google_utils
+from . import torch_utils  # torch_utils, google_utils
 
 # Set printoptions
 torch.set_printoptions(linewidth=320, precision=5, profile='long')
@@ -84,7 +84,7 @@ def check_anchors(dataset, model, thr=4.0, imgsz=640):
         r = wh[:, None] / k[None]
         x = torch.min(r, 1. / r).min(2)[0]  # ratio metric
         best = x.max(1)[0]  # best_x
-        return (best > 1. / thr).float().mean()  #  best possible recall
+        return (best > 1. / thr).float().mean()  # best possible recall
 
     bpr = metric(m.anchor_grid.clone().cpu().view(-1, 2))
     print('Best Possible Recall (BPR) = %.4f' % bpr, end='')