Loads a state_dict created by an earlier call to state_dict(). If ``fp16_optimizer_instance`` was constructed from some ``init_optimi

Returns a dict containing the current state of this :class:`FP16_Optimizer` instance. This dict contains attributes of :class:`FP16_O

If no closure is supplied, :attr:`step` should be called after ``fp16_optimizer_obj.backward(loss)``. :attr:`step` updates th

3x3 convolution with padding

Perform evaluation on COCO keypoint task :param cfg: cfg dictionary :param preds: prediction :param output_dir: outpu

Convert model to half precision in a batchnorm-safe way.

Designed to work with network_to_half. BatchNorm layers need parameters in single precision. Find all layers and convert them back to flo

Perform evaluation on COCO keypoint task :param cfg: cfg dictionary :param preds: prediction :param output_dir: outpu

:param model: :param input_tensors: :param item_length: :return:

Copy master parameters to model parameters. Args: model_params: List of model parameters created by :func:`prep_param_lists`.

Copy model gradients to master gradients. Args: model_params: List of model parameters created by :func:`prep_param_lists`.