Constructs a RepGhostNet model

Creates an EfficientNet-EdgeTPU model Ref impl: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet/edgetpu

Remove CLS token.

Generate MobileNet-V2 network Ref impl: https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/mobilenet_v2.py Paper:

Concat a list of DataProto. The batch is concatenated among dim=0. The meta_info is assumed to be identical and will use the first one.

3x3 convolution + batch norm

return info dicts for specified keys (or all if None) at specified indices (or out_indices if None)

Merge pre BN to reduce inference runtime.

Args: cfg (CspModelCfg): Model architecture configuration in_chans (int): Number of input channels (default: 3)

Constructs a GhostNet model

Creates an EfficientNet-CondConv model. Ref impl: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet/condconv

Creates an EfficientNet-V2 Small model Ref impl: https://github.com/google/automl/tree/master/efficientnetv2 Paper: `EfficientNetV2: Smaller

Creates a hardcorenas model Ref impl: https://github.com/Alibaba-MIIL/HardCoReNAS Paper: https://arxiv.org/abs/2102.11646

Creates a MixNet Medium-Large model. Ref impl: https://github.com/tensorflow/tpu/tree/master/models/official/mnasnet/mixnet Paper: https://ar

Generate bbox and apply lambda correction.

This is the equivalent of torch.repeat_interleave(x, dim=1, repeats=n_rep). The hidden states go from (batch, num_key_value_heads, seqlen, he

Resample the weights of the patch embedding kernel to target resolution. We resample the patch embedding kernel by approximately inverting the eff

Args: layers (List[int]) : number of layers in each block channels (List[int]) : number of channels in each block:

Parameters ---------- block (nn.Module): Bottleneck class. - For SENet154: SEBottleneck - For SE-ResN