8.1.1.7.1.2.1.2. blueoil.networks.keypoint_detection.lm_single_pose_v1
¶
8.1.1.7.1.2.1.2.1. Module Contents¶
8.1.1.7.1.2.1.2.1.1. Classes¶
LM original single-person pose estimation network. |
|
LM original quantized single-person pose estimation network. |
-
class
blueoil.networks.keypoint_detection.lm_single_pose_v1.
LmSinglePoseV1
(stride=2, *args, **kwargs)¶ Bases:
blueoil.networks.keypoint_detection.base.Base
LM original single-person pose estimation network.
-
loss
(self, output, labels)¶ Loss function for single-person pose estimation.
- Parameters
output – Tensor of network output. shape is (batch_size, height, width, num_joints).
labels – Tensor of ground-truth labels. shape is (batch_size, height, width, num_joints).
-
_get_lmnet_block
(self, is_training, channels_data_format)¶
-
_space_to_depth
(self, inputs=None, block_size=2, name='')¶
-
base
(self, images, is_training, *args, **kwargs)¶ Base function contains inference.
- Parameters
images – Input images.
is_training – A flag for if is training.
- Returns
Inference result.
- Return type
tf.Tensor
-
-
class
blueoil.networks.keypoint_detection.lm_single_pose_v1.
LmSinglePoseV1Quantize
(activation_quantizer=None, activation_quantizer_kwargs={}, weight_quantizer=None, weight_quantizer_kwargs={}, *args, **kwargs)¶ Bases:
blueoil.networks.keypoint_detection.lm_single_pose_v1.LmSinglePoseV1
LM original quantized single-person pose estimation network.
Following args are used for inference:
activation_quantizer
,activation_quantizer_kwargs
,weight_quantizer
,weight_quantizer_kwargs
.- Parameters
activation_quantizer (callable) – Weight quantizater. See more at blueoil.quantizations.
activation_quantizer_kwargs (dict) – Kwargs for activation_quantizer.
weight_quantizer (callable) – Activation quantizater. See more at blueoil.quantizations.
weight_quantizer_kwargs (dict) – Kwargs for weight_quantizer.
-
static
_quantized_variable_getter
(getter, name, weight_quantization=None, *args, **kwargs)¶ Get the quantized variables.
Use if to choose or skip the target should be quantized.
- Parameters
getter – Default from tensorflow.
name – Default from tensorflow.
weight_quantization – Callable object which quantize variable.
args – Args.
kwargs – Kwargs.