scripts/tf_cnn_benchmarks/models/resnet_model.py [57:74]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
  name = name_key + str(cnn.counts[name_key])
  cnn.counts[name_key] += 1

  with tf.variable_scope(name):
    if depth == in_size:
      if stride == 1:
        shortcut = input_layer
      else:
        shortcut = cnn.apool(
            1, 1, stride, stride, input_layer=input_layer,
            num_channels_in=in_size)
        mlperf.logger.log_projection(input_tensor=input_layer,
                                     output_tensor=shortcut)
    else:
      shortcut = cnn.conv(
          depth, 1, 1, stride, stride, activation=None,
          use_batch_norm=True, input_layer=input_layer,
          num_channels_in=in_size, bias=None)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



scripts/tf_cnn_benchmarks/models/resnet_model.py [109:126]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
  name = name_key + str(cnn.counts[name_key])
  cnn.counts[name_key] += 1

  with tf.variable_scope(name):
    if depth == in_size:
      if stride == 1:
        shortcut = input_layer
      else:
        shortcut = cnn.apool(
            1, 1, stride, stride, input_layer=input_layer,
            num_channels_in=in_size)
        mlperf.logger.log_projection(input_tensor=input_layer,
                                     output_tensor=shortcut)
    else:
      shortcut = cnn.conv(
          depth, 1, 1, stride, stride, activation=None,
          use_batch_norm=True, input_layer=input_layer,
          num_channels_in=in_size, bias=None)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -