Network architecture

Here is the dhsegment architecture definition

---

dh_segment.network.inference_vgg16(images, params, num_classes, use_batch_norm=False, weight_decay=0.0, is_training=False)

Return type

tensorflow.Tensor

dh_segment.network.inference_resnet_v1_50(images, params, num_classes, use_batch_norm=False, weight_decay=0.0, is_training=False)

Return type

tensorflow.Tensor

dh_segment.network.inference_u_net(images, params, num_classes, use_batch_norm=False, weight_decay=0.0, is_training=False)

Return type

tensorflow.Tensor

dh_segment.network.vgg_16_fn(input_tensor, scope='vgg_16', blocks=5, weight_decay=0.0005)

Return type

(tensorflow.Tensor, <class ‘list’>)

dh_segment.network.resnet_v1_50_fn(input_tensor, is_training=False, blocks=4, weight_decay=0.0001, renorm=True, corrected_version=False)

Return type

tensorflow.Tensor