basecls.models.regnet#

RegNet Series

RegNet X/Y: “Designing Network Design Spaces”

引用

facebookresearch/pycls facebookresearch/pycls

class basecls.models.regnet.RegBottleneckBlock(w_in, w_out, stride, bot_mul, group_w, se_r, norm_name, act_name, **kwargs)[源代码]#

基类：Module

Residual bottleneck block for RegNet: x + f(x), f = 1x1, 3x3 [+SE], 1x1.

forward(x)[源代码]#
class basecls.models.regnet.RegNet(stem_name, stem_w, block_name, depth, w0, wa, wm, group_w, stride=2, bot_mul=1.0, se_r=0.0, drop_path_prob=0.0, zero_init_final_gamma=False, norm_name='BN', act_name='relu', head=None)[源代码]#

基类：ResNet

RegNet model.

参数

  • stem_name (Union[str, Callable]) – stem name.

  • stem_w (int) – stem width.

  • block_name (Union[str, Callable]) – block name.

  • depth (int) – depth.

  • w0 (int) – initial width.

  • wa (float) – slope.

  • wm (float) – quantization.

  • group_w (int) – group width for each stage (applies to bottleneck block).

  • stride (int) – stride for each stage (applies to the first block of each stage). Default: 2

  • bot_mul (float) – bottleneck multiplier for each stage (applies to bottleneck block). Default: 1.0

  • se_r (float) – Squeeze-and-Excitation (SE) ratio. Default: 0.0

  • drop_path_prob (float) – drop path probability. Default: 0.0

  • zero_init_final_gamma (bool) – enable zero-initialize or not. Default: False

  • norm_name (str) – normalization function. Default: "BN"

  • act_name (str) – activation function. Default: "relu"

  • head (Optional[Mapping[str, Any]]) – head args. Default: None