8.1.1.7.2.2. `blueoil.networks.lmnet_multi`¶

8.1.1.7.2.2.1. Module Contents¶

8.1.1.7.2.2.1.1. Classes¶

Multi label prediction

8.1.1.7.2.2.1.2. Functions¶

safe_log(arg)

blueoil.networks.lmnet_multi.safe_log(arg)¶

class blueoil.networks.lmnet_multi.LmnetMulti¶

Multi label prediction

version = 0.01¶

property placeholders(self)¶: placeholders

inference(self, images, is_training)¶

inference.

Parameters

images – images tensor. shape is (batch_num, height, width, channel)
is_training –

loss(self, output, labels)¶

loss.

Parameters

output – network output sigmoided tensor.
labels – multi label encoded tensor. shape is (batch_num, num_classes)

metrics(self, output, labels, thresholds=[0.3, 0.5, 0.7])¶

metrics_for_each_class(self, output, labels, thresholds=[0.3, 0.5, 0.7])¶