webcam updates

detect.py

@@ -50,13 +50,16 @@ def detect(
 
  for i, (path, img, im0) in enumerate(dataloader):
  t = time.time()
- print("%g/%g '%s': " % (i + 1, len(dataloader), path if not webcam else 'webcam'), end='')
+ if webcam:
+ print('webcam frame %g: ' % (i + 1), end='')
+ else:
+ print('image %g/%g %s: ' % (i + 1, len(dataloader), path), end='')
  save_path = os.path.join(output, path.split('/')[-1])
 
  # Get detections
  img = torch.from_numpy(img).unsqueeze(0).to(device)
  if ONNX_EXPORT:
- torch.onnx._export(model, img, 'weights/model.onnx', verbose=True)
+ torch.onnx.export(model, img, 'weights/model.onnx', verbose=True)
  return # ONNX export
  pred = model(img)
  pred = pred[pred[:, :, 4] > conf_thres] # remove boxes < threshold
@@ -70,9 +73,9 @@ def detect(
 
  # Print results to screen
  unique_classes = detections[:, -1].cpu().unique()
- for i in unique_classes:
- n = (detections[:, -1].cpu() == i).sum()
- print('%g %ss' % (n, classes[int(i)]), end=', ')
+ for c in unique_classes:
+ n = (detections[:, -1].cpu() == c).sum()
+ print('%g %ss' % (n, classes[int(c)]), end=', ')
 
  # Draw bounding boxes and labels of detections
  for x1, y1, x2, y2, conf, cls_conf, cls in detections:

models.py

@@ -82,6 +82,9 @@ class EmptyLayer(nn.Module):
  def __init__(self):
  super(EmptyLayer, self).__init__()
 
+ def forward(self, x):
+ return x
+
 
 class Upsample(nn.Module):
  # Custom Upsample layer (nn.Upsample gives deprecated warning message)
@@ -121,8 +124,8 @@ def __init__(self, anchors, nC, img_dim, anchor_idxs, cfg):
 
  # Build anchor grids
  nG = int(self.img_dim / stride) # number grid points
- self.grid_x = torch.arange(nG).repeat(nG, 1).view([1, 1, nG, nG]).float()
- self.grid_y = torch.arange(nG).repeat(nG, 1).t().view([1, 1, nG, nG]).float()
+ self.grid_x = torch.arange(nG).repeat((nG, 1)).view((1, 1, nG, nG)).float()
+ self.grid_y = torch.arange(nG).repeat((nG, 1)).t().view((1, 1, nG, nG)).float()
  self.anchor_wh = torch.FloatTensor([(a_w / stride, a_h / stride) for a_w, a_h in anchors]) # scale anchors
  self.anchor_w = self.anchor_wh[:, 0].view((1, nA, 1, 1))
  self.anchor_h = self.anchor_wh[:, 1].view((1, nA, 1, 1))
@@ -169,8 +172,8 @@ def forward(self, p, targets=None, var=None):
  # Width and height (yolo method)
  w = p[..., 2] # Width
  h = p[..., 3] # Height
- width = torch.exp(w.data) * self.anchor_w
- height = torch.exp(h.data) * self.anchor_h
+ # width = torch.exp(w.data) * self.anchor_w
+ # height = torch.exp(h.data) * self.anchor_h
 
  # Width and height (power method)
  # w = torch.sigmoid(p[..., 2]) # Width
@@ -217,8 +220,8 @@ def forward(self, p, targets=None, var=None):
 
  # Broadcasting only supported on first dimension in CoreML. See onnx-coreml/_operators.py
  # p_cls = F.softmax(p_cls, 2) * p_conf # SSD-like conf
- p_cls = torch.exp(p_cls).permute(2, 1, 0)
- p_cls = p_cls / p_cls.sum(0).unsqueeze(0) * p_conf.permute(2, 1, 0) # F.softmax() equivalent
+ p_cls = torch.exp(p_cls).permute((2, 1, 0))
+ p_cls = p_cls / p_cls.sum(0).unsqueeze(0) * p_conf.permute((2, 1, 0)) # F.softmax() equivalent
  p_cls = p_cls.permute(2, 1, 0)
 
  return torch.cat((xy / nG, width_height, p_conf, p_cls), 2).squeeze().t()
@@ -246,6 +249,7 @@ def __init__(self, cfg_path, img_size=416):
  self.hyperparams, self.module_list = create_modules(self.module_defs)
  self.img_size = img_size
  self.loss_names = ['loss', 'x', 'y', 'w', 'h', 'conf', 'cls', 'nT']
+ self.losses = []
 
  def forward(self, x, targets=None, var=0):
  self.losses = defaultdict(float)
@@ -296,8 +300,8 @@ def load_darknet_weights(self, weights, cutoff=-1):
  if not os.path.isfile(weights):
  try:
  os.system('wget https://pjreddie.com/media/files/' + weights_file + ' -P ' + weights)
- except:
- assert os.path.isfile(weights)
+ except IOError:
+ print(weights + ' not found')
 
  # Establish cutoffs
  if weights_file == 'darknet53.conv.74':

train.py

@@ -36,7 +36,6 @@ def train(
 
  # Configure run
  data_cfg = parse_data_cfg(data_cfg)
- num_classes = int(data_cfg['classes'])
  train_path = data_cfg['train']
 
  # Initialize model
@@ -62,7 +61,7 @@ def train(
  # p.requires_grad = False
 
  # Set optimizer
- optimizer = torch.optim.SGD(filter(lambda p: p.requires_grad, model.parameters()), lr=lr0, momentum=.9)
+ optimizer = torch.optim.SGD(filter(lambda x: x.requires_grad, model.parameters()), lr=lr0, momentum=.9)
 
  start_epoch = checkpoint['epoch'] + 1
  if checkpoint['optimizer'] is not None:
@@ -85,7 +84,7 @@ def train(
  model.to(device).train()
 
  # Set optimizer
- optimizer = torch.optim.SGD(filter(lambda p: p.requires_grad, model.parameters()), lr=lr0, momentum=.9)
+ optimizer = torch.optim.SGD(filter(lambda x: x.requires_grad, model.parameters()), lr=lr0, momentum=.9)
 
  # Set scheduler
  # scheduler = torch.optim.lr_scheduler.MultiStepLR(optimizer, milestones=[54, 61], gamma=0.1)

utils/datasets.py

@@ -58,7 +58,6 @@ def __len__(self):
 class LoadWebcam: # for inference
  def __init__(self, img_size=416):
  self.cam = cv2.VideoCapture(0)
- self.nF = 9999 # number of image files
  self.height = img_size
 
  def __iter__(self):
@@ -88,7 +87,7 @@ def __next__(self):
  return img_path, img, img0
 
  def __len__(self):
- return self.nF # number of files
+ return 0
 
 
 class LoadImagesAndLabels: # for training

utils/parse_config.py

@@ -1,14 +1,12 @@
-
-
 def parse_model_config(path):
  """Parses the yolo-v3 layer configuration file and returns module definitions"""
  file = open(path, 'r')
  lines = file.read().split('\n')
  lines = [x for x in lines if x and not x.startswith('#')]
- lines = [x.rstrip().lstrip() for x in lines] # get rid of fringe whitespaces
+ lines = [x.rstrip().lstrip() for x in lines]  # get rid of fringe whitespaces
  module_defs = []
  for line in lines:
- if line.startswith('['): # This marks the start of a new block
+ if line.startswith('['):  # This marks the start of a new block
  module_defs.append({})
  module_defs[-1]['type'] = line[1:-1].rstrip()
  if module_defs[-1]['type'] == 'convolutional':
@@ -20,6 +18,7 @@ def parse_model_config(path):
 
  return module_defs
 
+
 def parse_data_cfg(path):
  """Parses the data configuration file"""
  options = dict()

utils/utils.py

@@ -254,7 +254,7 @@ def build_targets(target, anchor_wh, nA, nC, nG):
  iou_order = torch.argsort(-iou_best) # best to worst
 
  # Unique anchor selection
- u = torch.cat((gi, gj, a), 0).view(3, -1)
+ u = torch.cat((gi, gj, a), 0).view((3, -1))
  _, first_unique = np.unique(u[:, iou_order], axis=1, return_index=True) # first unique indices
  # _, first_unique = torch.unique(u[:, iou_order], dim=1, return_inverse=True) # different than numpy?
 
@@ -340,7 +340,8 @@ def non_max_suppression(prediction, conf_thres=0.5, nms_thres=0.4):
  # x = np.concatenate((log_w.reshape(-1, 1), log_h.reshape(-1, 1)), 1)
  # from scipy.stats import multivariate_normal
  # for c in range(60):
- # shape_likelihood[:, c] = multivariate_normal.pdf(x, mean=mat['class_mu'][c, :2], cov=mat['class_cov'][c, :2, :2])
+ # shape_likelihood[:, c] =
+ # multivariate_normal.pdf(x, mean=mat['class_mu'][c, :2], cov=mat['class_cov'][c, :2, :2])
 
  class_prob, class_pred = torch.max(F.softmax(pred[:, 5:], 1), 1)
 
@@ -436,7 +437,6 @@ def coco_class_count(path='../coco/labels/train2014/'):
 def plot_results():
  # Plot YOLO training results file 'results.txt'
  import glob
- import numpy as np
  import matplotlib.pyplot as plt
  # import os; os.system('rm -rf results.txt && wget https://storage.googleapis.com/ultralytics/results_v1_0.txt')