Python cfg.RNG_SEED属性代码示例

# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import RNG_SEED [as 别名]
def construct_graph(self):
    # Set the random seed
    torch.manual_seed(cfg.RNG_SEED)
    # Build the main computation graph
    self.net.create_architecture(self.imdb.num_classes, tag='default')
    # Define the loss
    # loss = layers['total_loss']
    # Set learning rate and momentum
    lr = cfg.TRAIN.LEARNING_RATE
    params = []
    for key, value in dict(self.net.named_parameters()).items():
      if value.requires_grad:
        if 'bias' in key:
          params += [{'params':[value],'lr':lr*(cfg.TRAIN.DOUBLE_BIAS + 1), 'weight_decay': cfg.TRAIN.BIAS_DECAY and cfg.TRAIN.WEIGHT_DECAY or 0}]
        else:
          params += [{'params':[value],'lr':lr, 'weight_decay': cfg.TRAIN.WEIGHT_DECAY}]
    self.optimizer = torch.optim.SGD(params, momentum=cfg.TRAIN.MOMENTUM)
    # Write the train and validation information to tensorboard
    self.writer = tb.writer.FileWriter(self.tbdir)
   # self.valwriter = tb.writer.FileWriter(self.tbvaldir)

    return lr, self.optimizer 

# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import RNG_SEED [as 别名]
def construct_graph(self):
    # Set the random seed
    torch.manual_seed(cfg.RNG_SEED)
    # Build the main computation graph
    self.net.create_architecture(self.imdb.num_classes, tag='default',
                                            anchor_scales=cfg.ANCHOR_SCALES,
                                            anchor_ratios=cfg.ANCHOR_RATIOS)
    # Define the loss
    # loss = layers['total_loss']
    # Set learning rate and momentum
    lr = cfg.TRAIN.LEARNING_RATE
    params = []
    for key, value in dict(self.net.named_parameters()).items():
      if value.requires_grad:
        if 'bias' in key:
          params += [{'params':[value],'lr':lr*(cfg.TRAIN.DOUBLE_BIAS + 1), 'weight_decay': cfg.TRAIN.BIAS_DECAY and cfg.TRAIN.WEIGHT_DECAY or 0}]
        else:
          params += [{'params':[value],'lr':lr, 'weight_decay': cfg.TRAIN.WEIGHT_DECAY}]
    self.optimizer = torch.optim.SGD(params, momentum=cfg.TRAIN.MOMENTUM)
    # Write the train and validation information to tensorboard
    self.writer = tb.writer.FileWriter(self.tbdir)
    self.valwriter = tb.writer.FileWriter(self.tbvaldir)

    return lr, self.optimizer 

# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import RNG_SEED [as 别名]
def test_net(sess, net, imdb, weights_filename, thresh=0.05):
    np.random.seed(cfg.RNG_SEED)
    """Test a SSH network on an image database."""
    num_images = len(imdb.image_index)
    # all detections are collected into:
    #  all_boxes[cls][image] = N x 5 array of detections in
    #  (x1, y1, x2, y2, score)
    all_boxes = [[] for _ in range(num_images)]

    output_dir = get_output_dir(imdb, weights_filename)
    # timers
    _t = {'im_detect': Timer(), 'misc': Timer()}

    for i in range(num_images):
        im = cv2.imread(imdb.image_path_at(i))

        _t['im_detect'].tic()
        scores, boxes = im_detect(sess, net, im)
        _t['im_detect'].toc()

        _t['misc'].tic()

        inds = np.where(scores[:, 0] > thresh)[0]
        scores = scores[inds, 0]
        boxes = boxes[inds, :]
        dets = np.hstack((boxes, scores[:, np.newaxis])).astype(np.float32, copy=False)
        keep = nms(dets, cfg.TEST.NMS)
        dets = dets[keep, :]
        all_boxes[i] = det
        _t['misc'].toc()

        print('im_detect: {:d}/{:d} {:.3f}s {:.3f}s' \
              .format(i + 1, num_images, _t['im_detect'].average_time,
                      _t['misc'].average_time))

    det_file = os.path.join(output_dir, 'detections.pkl')
    with open(det_file, 'wb') as f:
        pickle.dump(all_boxes, f, pickle.HIGHEST_PROTOCOL)

    print('Evaluating detections')
    imdb.evaluate_detections(all_boxes, output_dir) 

# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import RNG_SEED [as 别名]
def construct_graph(self, sess):
    with sess.graph.as_default():
      # Set the random seed for tensorflow
      tf.set_random_seed(cfg.RNG_SEED)
      # Build the main computation graph
      layers = self.net.create_architecture('TRAIN', self.imdb.num_classes, tag='default',
                                            anchor_scales=cfg.ANCHOR_SCALES,
                                            anchor_ratios=cfg.ANCHOR_RATIOS)
      # Define the loss
      loss = layers['total_loss']
      # Set learning rate and momentum
      lr = tf.Variable(cfg.TRAIN.LEARNING_RATE, trainable=False)
      self.optimizer = tf.train.MomentumOptimizer(lr, cfg.TRAIN.MOMENTUM)

      # Compute the gradients with regard to the loss
      gvs = self.optimizer.compute_gradients(loss)
      # Double the gradient of the bias if set
      if cfg.TRAIN.DOUBLE_BIAS:
        final_gvs = []
        with tf.variable_scope('Gradient_Mult') as scope:
          for grad, var in gvs:
            scale = 1.
            if cfg.TRAIN.DOUBLE_BIAS and '/biases:' in var.name:
              scale *= 2.
            if not np.allclose(scale, 1.0):
              grad = tf.multiply(grad, scale)
            final_gvs.append((grad, var))
        train_op = self.optimizer.apply_gradients(final_gvs)
      else:
        train_op = self.optimizer.apply_gradients(gvs)

      # We will handle the snapshots ourselves
      self.saver = tf.train.Saver(max_to_keep=100000)
      # Write the train and validation information to tensorboard
      self.writer = tf.summary.FileWriter(self.tbdir, sess.graph)
      self.valwriter = tf.summary.FileWriter(self.tbvaldir)

    return lr, train_op 

# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import RNG_SEED [as 别名]
def test_net_base(sess, net, imdb, roidb, weights_filename, visualize=False):
  np.random.seed(cfg.RNG_SEED)
  """Test a Fast R-CNN network on an image database."""
  num_images = len(roidb)
  output_dir = get_output_dir(imdb, weights_filename)
  output_dir_image = os.path.join(output_dir, 'images')
  if visualize and not os.path.exists(output_dir_image):
    os.makedirs(output_dir_image)
  all_scores = [[] for _ in range(num_images)]

  # timers
  _t = {'score' : Timer()}

  for i in range(num_images):
    _t['score'].tic()
    all_scores[i], blobs = im_detect(sess, imdb, net, [roidb[i]])
    _t['score'].toc()

    print('score: {:d}/{:d} {:.3f}s' \
        .format(i + 1, num_images, _t['score'].average_time))

    if visualize and i % 10 == 0:
      basename = os.path.basename(imdb.image_path_at(i)).split('.')[0]
      im_vis, wrong = draw_predicted_boxes_test(blobs['data'], all_scores[i], blobs['gt_boxes'])
      if wrong:
        out_image = os.path.join(output_dir_image, basename + '.jpg')
        print(out_image)
        cv2.imwrite(out_image, im_vis)

  res_file = os.path.join(output_dir, 'results.pkl')
  with open(res_file, 'wb') as f:
    pickle.dump(all_scores, f, pickle.HIGHEST_PROTOCOL)

  print('Evaluating detections')
  mcls_sc, mcls_ac, mcls_ap, mins_sc, mins_ac, mins_ap = imdb.evaluate(all_scores, output_dir)
  eval_file = os.path.join(output_dir, 'results.txt')
  with open(eval_file, 'w') as f:
    f.write('{:.3f} {:.3f} {:.3f} {:.3f}'.format(mins_ap, mins_ac, mcls_ap, mcls_ac)) 

# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import RNG_SEED [as 别名]
def test_net_memory(sess, net, imdb, roidb, weights_filename, visualize=False, iter=0):
  np.random.seed(cfg.RNG_SEED)
  """Test a Fast R-CNN network on an image database."""
  num_images = len(roidb)
  output_dir = get_output_dir(imdb, weights_filename + "_iter%02d" % iter)
  output_dir_image = os.path.join(output_dir, 'images')
  if visualize and not os.path.exists(output_dir_image):
    os.makedirs(output_dir_image)
  all_scores = [[] for _ in range(num_images)]

  # timers
  _t = {'score' : Timer()}

  for i in range(num_images):
    _t['score'].tic()
    all_scores[i], blobs = im_detect_iter(sess, imdb, net, [roidb[i]], iter)
    _t['score'].toc()

    print('score: {:d}/{:d} {:.3f}s' \
        .format(i + 1, num_images, _t['score'].average_time))

    if visualize and i % 10 == 0:
      basename = os.path.basename(imdb.image_path_at(i)).split('.')[0]
      im_vis, wrong = draw_predicted_boxes_test(blobs['data'], all_scores[i], blobs['gt_boxes'])
      if wrong:
        out_image = os.path.join(output_dir_image, basename + '.jpg')
        print(out_image)
        cv2.imwrite(out_image, im_vis)

  res_file = os.path.join(output_dir, 'results.pkl')
  with open(res_file, 'wb') as f:
    pickle.dump(all_scores, f, pickle.HIGHEST_PROTOCOL)

  print('Evaluating detections')
  mcls_sc, mcls_ac, mcls_ap, mins_sc, mins_ac, mins_ap = imdb.evaluate(all_scores, output_dir)
  eval_file = os.path.join(output_dir, 'results.txt')
  with open(eval_file, 'w') as f:
    f.write('{:.3f} {:.3f} {:.3f} {:.3f}'.format(mins_ap, mins_ac, mcls_ap, mcls_ac)) 

# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import RNG_SEED [as 别名]
def test_net(net, imdb, weights_filename, max_per_image=100, thresh=0.):
  np.random.seed(cfg.RNG_SEED)
  """Test a Fast R-CNN network on an image database."""
  num_images = len(imdb.image_index)
  # all detections are collected into:
  #  all_boxes[cls][image] = N x 5 array of detections in
  #  (x1, y1, x2, y2, score)
  all_boxes = [[[] for _ in range(num_images)]
         for _ in range(imdb.num_classes)]

  output_dir = get_output_dir(imdb, weights_filename)
  # timers
  _t = {'im_detect' : Timer(), 'misc' : Timer()}

  for i in range(num_images):
    im = cv2.imread(imdb.image_path_at(i))

    _t['im_detect'].tic()
    scores, boxes = im_detect(net, im)
    _t['im_detect'].toc()

    _t['misc'].tic()

    # skip j = 0, because it's the background class
    for j in range(1, imdb.num_classes):
      inds = np.where(scores[:, j] > thresh)[0]
      cls_scores = scores[inds, j]
      cls_boxes = boxes[inds, j*4:(j+1)*4]
      cls_dets = np.hstack((cls_boxes, cls_scores[:, np.newaxis])) \
        .astype(np.float32, copy=False)
      keep = nms(torch.from_numpy(cls_dets), cfg.TEST.NMS).numpy() if cls_dets.size > 0 else []
      cls_dets = cls_dets[keep, :]
      all_boxes[j][i] = cls_dets

    # Limit to max_per_image detections *over all classes*
    if max_per_image > 0:
      image_scores = np.hstack([all_boxes[j][i][:, -1]
                    for j in range(1, imdb.num_classes)])
      if len(image_scores) > max_per_image:
        image_thresh = np.sort(image_scores)[-max_per_image]
        for j in range(1, imdb.num_classes):
          keep = np.where(all_boxes[j][i][:, -1] >= image_thresh)[0]
          all_boxes[j][i] = all_boxes[j][i][keep, :]
    _t['misc'].toc()

    print('im_detect: {:d}/{:d} {:.3f}s {:.3f}s' \
        .format(i + 1, num_images, _t['im_detect'].average_time(),
            _t['misc'].average_time()))

  det_file = os.path.join(output_dir, 'detections.pkl')
  with open(det_file, 'wb') as f:
    pickle.dump(all_boxes, f, pickle.HIGHEST_PROTOCOL)

  print('Evaluating detections')
  imdb.evaluate_detections(all_boxes, output_dir) 

# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import RNG_SEED [as 别名]
def convert_from_depre(net, imdb, input_dir, output_dir, snapshot, max_iters):
  if not osp.exists(output_dir):
    os.makedirs(output_dir)

  tfconfig = tf.ConfigProto(allow_soft_placement=True)
  tfconfig.gpu_options.allow_growth = True
  sess = tf.Session(config=tfconfig)

  num_classes = imdb.num_classes
  with sess.graph.as_default():
    tf.set_random_seed(cfg.RNG_SEED)
    layers = net.create_architecture(sess, 'TRAIN', num_classes, tag='default',
                                            anchor_scales=cfg.ANCHOR_SCALES,
                                            anchor_ratios=cfg.ANCHOR_RATIOS)
    loss = layers['total_loss']
    # Learning rate should be reduced already
    lr = tf.Variable(cfg.TRAIN.LEARNING_RATE * cfg.TRAIN.GAMMA, trainable=False)
    momentum = cfg.TRAIN.MOMENTUM
    optimizer = tf.train.MomentumOptimizer(lr, momentum)
    gvs = optimizer.compute_gradients(loss)
    if cfg.TRAIN.DOUBLE_BIAS:
      final_gvs = []
      with tf.variable_scope('Gradient_Mult') as scope:
        for grad, var in gvs:
          scale = 1.
          if cfg.TRAIN.DOUBLE_BIAS and '/biases:' in var.name:
            scale *= 2.
          if not np.allclose(scale, 1.0):
            grad = tf.multiply(grad, scale)
          final_gvs.append((grad, var))
      train_op = optimizer.apply_gradients(final_gvs)
    else:
      train_op = optimizer.apply_gradients(gvs)

    checkpoint = osp.join(input_dir, snapshot + '.ckpt')
    variables = tf.global_variables()
    name2var = {convert_names(v.name): v for v in variables}
    target_names = get_variables_in_checkpoint_file(checkpoint)
    restorer = tf.train.Saver(name2var)
    saver = tf.train.Saver()

    print('Importing...')
    restorer.restore(sess, checkpoint)
    checkpoint = osp.join(output_dir, snapshot + '.ckpt')
    print('Exporting...')
    saver.save(sess, checkpoint)

    # also copy the pkl file
    index = osp.join(input_dir, snapshot + '.pkl')
    outdex = osp.join(output_dir, snapshot + '.pkl')
    shutil.copy(index, outdex)

  sess.close() 

# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import RNG_SEED [as 别名]
def construct_graph(self, sess):
        with sess.graph.as_default():
            # Set the random seed for tensorflow
            tf.set_random_seed(cfg.RNG_SEED)
            # Build the main computation graph
            layers = self.net.create_architecture('TRAIN', self.imdb.num_classes, tag='default',
                                                  anchor_width=cfg.CTPN.ANCHOR_WIDTH,
                                                  anchor_h_ratio_step=cfg.CTPN.H_RADIO_STEP,
                                                  num_anchors=cfg.CTPN.NUM_ANCHORS)
            # Define the loss
            total_loss = layers['total_loss']
            # Set learning rate and momentum
            lr = tf.Variable(cfg.TRAIN.LEARNING_RATE, trainable=False)


            if cfg.TRAIN.OPTIMIZER == 'Adam':
                self.optimizer = tf.train.AdamOptimizer(lr)
            elif cfg.TRAIN.OPTIMIZER == 'Momentum':
                self.optimizer = tf.train.MomentumOptimizer(lr, cfg.TRAIN.MOMENTUM)
            elif cfg.TRAIN.OPTIMIZER == 'RMS':
                self.optimizer = tf.train.RMSPropOptimizer(lr)
            else:
                raise NotImplementedError

            global_step = tf.Variable(0, trainable=False)
            with_clip = False
            if with_clip:
                tvars = tf.trainable_variables()
                grads, norm = tf.clip_by_global_norm(tf.gradients(total_loss, tvars), 10.0)
                train_op = self.optimizer.apply_gradients(list(zip(grads, tvars)), global_step=global_step)
            else:
                # required by tf.layers.batch_normalization()
                # add update ops(for moving_mean and moving_variance) as a dependency to the train_op
                # https://www.tensorflow.org/api_docs/python/tf/layers/batch_normalization
                update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
                with tf.control_dependencies(update_ops):
                    train_op = self.optimizer.minimize(total_loss, global_step=global_step)

            # We will handle the snapshots ourselves
            self.saver = tf.train.Saver(max_to_keep=100000)
            # Write the train and validation information to tensorboard
            self.writer = tf.summary.FileWriter(self.tbdir, sess.graph)
            self.valwriter = tf.summary.FileWriter(self.tbvaldir)

        return lr, train_op 

# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import RNG_SEED [as 别名]
def test_net(sess, net, imdb, weights_filename, max_per_image=100, thresh=0.0):
  np.random.seed(cfg.RNG_SEED)
  """Test a Fast R-CNN network on an image database."""
  num_images = len(imdb.image_index)
  # all detections are collected into:
  #  all_boxes[cls][image] = N x 5 array of detections in
  #  (x1, y1, x2, y2, score)
  all_boxes = [[[] for _ in range(num_images)]
         for _ in range(imdb.num_classes)]

  output_dir = get_output_dir(imdb, weights_filename)
  if os.path.isfile(os.path.join(output_dir, 'detections.pkl')):
    all_boxes=pickle.load(open(os.path.join(output_dir, 'detections.pkl'),'r'))
  else:  
    # timers
    _t = {'im_detect' : Timer(), 'misc' : Timer()}

    for i in range(num_images):
      im = cv2.imread(imdb.image_path_at(i))

      _t['im_detect'].tic()
      scores, boxes,_ ,_ = im_detect(sess, net, im)
      _t['im_detect'].toc()

      _t['misc'].tic()

      # skip j = 0, because it's the background class
      for j in range(1, imdb.num_classes):
        inds = np.where(scores[:, j] > thresh)[0]
        cls_scores = scores[inds, j]
        cls_boxes = boxes[inds, j*4:(j+1)*4]
        cls_dets = np.hstack((cls_boxes, cls_scores[:, np.newaxis])) \
          .astype(np.float32, copy=False)
        keep = nms(cls_dets, cfg.TEST.NMS)
        cls_dets = cls_dets[keep, :]
        all_boxes[j][i] = cls_dets

      # Limit to max_per_image detections *over all classes*
      if max_per_image > 0:
        image_scores = np.hstack([all_boxes[j][i][:, -1]
                      for j in range(1, imdb.num_classes)])
        if len(image_scores) > max_per_image:
          image_thresh = np.sort(image_scores)[-max_per_image]
          for j in range(1, imdb.num_classes):
            keep = np.where(all_boxes[j][i][:, -1] >= image_thresh)[0]
            all_boxes[j][i] = all_boxes[j][i][keep, :]
      _t['misc'].toc()

      print('im_detect: {:d}/{:d} {:.3f}s {:.3f}s' \
          .format(i + 1, num_images, _t['im_detect'].average_time,
              _t['misc'].average_time))

    det_file = os.path.join(output_dir, 'detections_{:f}.pkl'.format(10))
    with open(det_file, 'wb') as f:
      pickle.dump(all_boxes, f, pickle.HIGHEST_PROTOCOL)

  print('Evaluating detections')
  imdb.evaluate_detections(all_boxes, output_dir) 

# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import RNG_SEED [as 别名]
def test_net(sess, net, imdb, weights_filename, max_per_image=100, thresh=0.):
  np.random.seed(cfg.RNG_SEED)
  """Test a Fast R-CNN network on an image database."""
  num_images = len(imdb.image_index)
  # all detections are collected into:
  #  all_boxes[cls][image] = N x 5 array of detections in
  #  (x1, y1, x2, y2, score)
  all_boxes = [[[] for _ in range(num_images)]
         for _ in range(imdb.num_classes)]

  output_dir = get_output_dir(imdb, weights_filename)
  # timers
  _t = {'im_detect' : Timer(), 'misc' : Timer()}

  for i in range(num_images):
    im = cv2.imread(imdb.image_path_at(i))

    _t['im_detect'].tic()
    scores, boxes = im_detect(sess, net, im)
    _t['im_detect'].toc()

    _t['misc'].tic()

    # skip j = 0, because it's the background class
    for j in range(1, imdb.num_classes):
      inds = np.where(scores[:, j] > thresh)[0]
      cls_scores = scores[inds, j]
      cls_boxes = boxes[inds, j*4:(j+1)*4]
      cls_dets = np.hstack((cls_boxes, cls_scores[:, np.newaxis])) \
        .astype(np.float32, copy=False)
      keep = nms(cls_dets, cfg.TEST.NMS)
      cls_dets = cls_dets[keep, :]
      all_boxes[j][i] = cls_dets

    # Limit to max_per_image detections *over all classes*
    if max_per_image > 0:
      image_scores = np.hstack([all_boxes[j][i][:, -1]
                    for j in range(1, imdb.num_classes)])
      if len(image_scores) > max_per_image:
        image_thresh = np.sort(image_scores)[-max_per_image]
        for j in range(1, imdb.num_classes):
          keep = np.where(all_boxes[j][i][:, -1] >= image_thresh)[0]
          all_boxes[j][i] = all_boxes[j][i][keep, :]
    _t['misc'].toc()

    print('im_detect: {:d}/{:d} {:.3f}s {:.3f}s' \
        .format(i + 1, num_images, _t['im_detect'].average_time,
            _t['misc'].average_time))

  det_file = os.path.join(output_dir, 'detections.pkl')
  with open(det_file, 'wb') as f:
    pickle.dump(all_boxes, f, pickle.HIGHEST_PROTOCOL)

  print('Evaluating detections')
  imdb.evaluate_detections(all_boxes, output_dir) 

# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import RNG_SEED [as 别名]
def construct_graph(self, sess):
    with sess.graph.as_default():
      # Set the random seed for tensorflow
      tf.set_random_seed(cfg.RNG_SEED)
      # Build the main computation graph
      layers = self.net.create_architecture('TRAIN', self.imdb.num_classes, tag='default')
      # Define the loss
      loss = layers['total_loss']
      # Set learning rate and momentum
      lr = tf.Variable(cfg.TRAIN.RATE, trainable=False)
      self.optimizer = tf.train.MomentumOptimizer(lr, cfg.TRAIN.MOMENTUM)

      # Compute the gradients with regard to the loss
      gvs = self.optimizer.compute_gradients(loss)
      grad_summaries = []
      for grad, var in gvs:
        if 'SMN' not in var.name and 'GMN' not in var.name:
          continue
        grad_summaries.append(tf.summary.histogram('TRAIN/' + var.name, var))
        if grad is not None:
          grad_summaries.append(tf.summary.histogram('GRAD/' + var.name, grad))

      # Double the gradient of the bias if set
      if cfg.TRAIN.DOUBLE_BIAS:
        final_gvs = []
        with tf.variable_scope('Gradient_Mult') as scope:
          for grad, var in gvs:
            scale = 1.
            if cfg.TRAIN.DOUBLE_BIAS and '/biases:' in var.name:
              scale *= 2.
            if not np.allclose(scale, 1.0):
              grad = tf.multiply(grad, scale)
            final_gvs.append((grad, var))
        train_op = self.optimizer.apply_gradients(final_gvs)
      else:
        train_op = self.optimizer.apply_gradients(gvs)
      self.summary_grads = tf.summary.merge(grad_summaries)

      # We will handle the snapshots ourselves
      self.saver = tf.train.Saver(max_to_keep=100000)
      # Write the train and validation information to tensorboard
      self.writer = tf.summary.FileWriter(self.tbdir, sess.graph)
      self.valwriter = tf.summary.FileWriter(self.tbvaldir)

    return lr, train_op 

# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import RNG_SEED [as 别名]
def construct_graph(self, sess):
    with sess.graph.as_default():
      # Set the random seed for tensorflow
      tf.set_random_seed(cfg.RNG_SEED)
      # Build the main computation graph
      layers = self.net.create_architecture('TRAIN', self.imdb.num_classes, tag='default')
      # Define the loss
      loss = layers['total_loss']
      # Set learning rate and momentum
      lr = tf.Variable(cfg.TRAIN.RATE, trainable=False)
      self.optimizer = tf.train.MomentumOptimizer(lr, cfg.TRAIN.MOMENTUM)

      # Compute the gradients with regard to the loss
      gvs = self.optimizer.compute_gradients(loss)
      grad_summaries = []
      for grad, var in gvs:
        if grad == None:
          continue
        grad_summaries.append(tf.summary.histogram('TRAIN/' + var.name, var))
        grad_summaries.append(tf.summary.histogram('GRAD/' + var.name, grad))

      # Double the gradient of the bias if set
      if cfg.TRAIN.DOUBLE_BIAS:
        final_gvs = []
        with tf.variable_scope('Gradient_Mult') as scope:
          for grad, var in gvs:
            scale = 1.
            if cfg.TRAIN.DOUBLE_BIAS and '/biases:' in var.name:
              scale *= 2.
            if not np.allclose(scale, 1.0):
              grad = tf.multiply(grad, scale)
            final_gvs.append((grad, var))
        train_op = self.optimizer.apply_gradients(final_gvs)
      else:
        train_op = self.optimizer.apply_gradients(gvs)
      self.summary_grads = tf.summary.merge(grad_summaries)

      # We will handle the snapshots ourselves
      self.saver = tf.train.Saver(max_to_keep=100000)
      # Write the train and validation information to tensorboard
      self.writer = tf.summary.FileWriter(self.tbdir, sess.graph)
      self.valwriter = tf.summary.FileWriter(self.tbvaldir)

    return lr, train_op 

# 需要导入模块: from model.config import cfg [as 别名]
# 或者: from model.config.cfg import RNG_SEED [as 别名]
def construct_graph(self):
    # Set the random seed
    torch.manual_seed(cfg.RNG_SEED)
    # Build the main computation graph
    self.net.create_architecture(self.imdb.num_classes, tag='default',
                                            anchor_scales=cfg.ANCHOR_SCALES,
                                            anchor_ratios=cfg.ANCHOR_RATIOS)
    # Define the loss
    # loss = layers['total_loss']
    # Set learning rate and momentum
    lr = cfg.TRAIN.LEARNING_RATE
    params = []
    for key, value in dict(self.net.named_parameters()).items():
      if value.requires_grad:
        if 'mask' in key:
          if 'bias' in key:
            params += [{'params': [value], 'lr': 10*lr * (cfg.TRAIN.DOUBLE_BIAS + 1),
                        'weight_decay': cfg.TRAIN.BIAS_DECAY and cfg.TRAIN.WEIGHT_DECAY or 0}]
          else:
            params += [{'params': [value], 'lr': 10*lr, 'weight_decay': cfg.TRAIN.WEIGHT_DECAY}]
        elif 'lightrcnn' in key:
          if 'bias' in key:
            params += [{'params': [value], 'lr': 10 * lr * (cfg.TRAIN.DOUBLE_BIAS + 1),
                        'weight_decay': cfg.TRAIN.BIAS_DECAY and cfg.TRAIN.WEIGHT_DECAY or 0}]
          else:
            params += [{'params': [value], 'lr': 10 * lr, 'weight_decay': cfg.TRAIN.WEIGHT_DECAY}]
        else:
          if 'bias' in key:
            params += [{'params': [value], 'lr': lr * (cfg.TRAIN.DOUBLE_BIAS + 1),
                        'weight_decay': cfg.TRAIN.BIAS_DECAY and cfg.TRAIN.WEIGHT_DECAY or 0}]
          else:
            params += [{'params': [value], 'lr': lr, 'weight_decay': cfg.TRAIN.WEIGHT_DECAY}]

        # if 'features' in key or 'classifier' in key or 'net' in key:
        #   if 'bias' in key:
        #     params += [{'params':[value],'lr':lr*(cfg.TRAIN.DOUBLE_BIAS + 1), 'weight_decay': cfg.TRAIN.BIAS_DECAY and cfg.TRAIN.WEIGHT_DECAY or 0}]
        #   else:
        #     params += [{'params':[value],'lr':lr, 'weight_decay': cfg.TRAIN.WEIGHT_DECAY}]
        # elif 'dec_channel' in key or 'global' in key:
        #   if 'bias' in key:
        #     params += [{'params': [value], 'lr': lr * (cfg.TRAIN.DOUBLE_BIAS + 1)*10,
        #                 'weight_decay': cfg.TRAIN.BIAS_DECAY and cfg.TRAIN.WEIGHT_DECAY or 0}]
        #   else:
        #     params += [{'params': [value], 'lr': lr*10, 'weight_decay': cfg.TRAIN.WEIGHT_DECAY}]
    self.optimizer = torch.optim.SGD(params, momentum=cfg.TRAIN.MOMENTUM)
    # Write the train and validation information to tensorboard
    self.writer = tb.writer.FileWriter(self.tbdir)
    self.valwriter = tb.writer.FileWriter(self.tbvaldir)

    return lr, self.optimizer