spandrel.architectures.RGT.RGT

class documentation

class RGT(nn.Module): (source)

Constructor: RGT(img_size, in_chans, embed_dim, depth, ...)

Undocumented

Method	`__init__`	Undocumented
Method	`forward`	Input: x: (B, C, H, W)
Method	`forward_features`	Undocumented
Class Variable	`hyperparameters`	Undocumented
Instance Variable	`before_RG`	Undocumented
Instance Variable	`conv_after_body`	Undocumented
Instance Variable	`conv_before_upsample`	Undocumented
Instance Variable	`conv_first`	Undocumented
Instance Variable	`conv_last`	Undocumented
Instance Variable	`embed_dim`	Undocumented
Instance Variable	`img_range`	Undocumented
Instance Variable	`layers`	Undocumented
Instance Variable	`mean`	Undocumented
Instance Variable	`norm`	Undocumented
Instance Variable	`num_features`	Undocumented
Instance Variable	`num_layers`	Undocumented
Instance Variable	`upsample`	Undocumented
Instance Variable	`upscale`	Undocumented
Instance Variable	`use_chk`	Undocumented

def __init__(self, *, img_size=64, in_chans=3, embed_dim=180, depth=[2, 2, 2, 2], num_heads=[2, 2, 2, 2], mlp_ratio=4.0, qkv_bias=True, qk_scale=None, drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.1, act_layer=nn.GELU, norm_layer=nn.LayerNorm, use_chk=False, upscale=2, img_range=1.0, resi_connection='1conv', split_size=[8, 8], c_ratio=0.5): (source) ¶

Undocumented

def forward(self, x): (source) ¶

Input: x: (B, C, H, W)

def forward_features(self, x): (source) ¶

Undocumented

hyperparameters: dict = (source) ¶

Undocumented

before_RG = (source) ¶

Undocumented

conv_after_body = (source) ¶

Undocumented

conv_before_upsample = (source) ¶