def loss_l2reg(pred, target, **kwargs): # batchSize=Sne
"""Add L2Loss to all the trainable variables.
Add summary for "Loss" and "Loss/avg".
Args:
logits: Logits from inference().
labels: Labels from distorted_inputs or inputs(). 1-D tensor
of shape [batch_size, heatmap_size ]
Returns:
Loss tensor of type float.
"""
clsf_loss_name = kwargs['lossFunction']
loss_clsf = model_base.loss_l2reg(pred['clsf'], target['clsf'],
pred['l2reg'], **kwargs)
kwargs['lossFunction'] = 'deconv'
#loss_deconv = tf.multiply(model_base.loss_l2reg(pred['deconv'], target['deconv'], 0, **kwargs), 1)#.1)
loss_deconv = model_base.loss_l2reg(pred['deconv'], target['deconv'], 0,
**kwargs)
total_loss = tf.add(loss_clsf, loss_deconv, name='loss_total')
return total_loss
def loss_l2reg(pred, target, l2reg, **kwargs): # batchSize=Sne
"""Add L2Loss to all the trainable variables.
Add summary for "Loss" and "Loss/avg".
Args:
logits: Logits from inference().
labels: Labels from distorted_inputs or inputs(). 1-D tensor
of shape [batch_size, heatmap_size ]
Returns:
Loss tensor of type float.
"""
return model_base.loss_l2reg(pred, target, l2reg, **kwargs)