rcan unshuffle options, docs, schema

docs/source/arch_reference.md

@@ -839,6 +839,7 @@ kernel_size: 3
 reduction: 16
 res_scale: 1
 act_mode: relu
+unshuffle_mod: false
 ```
 ### RGT
 #### rgt

options/onnx/RCAN/RCAN.yml

@@ -12,6 +12,7 @@ num_gpu: auto
 # Generator model settings
 network_g:
   type: rcan
+  unshuffle_mod: true # has no effect on scales larger than 2. for scales 1 and 2, setting to true speeds up the model and reduces vram usage significantly, but reduces quality.
 
 ############################
 # Pretrain and Resume Paths

options/test/RCAN/RCAN.yml

@@ -30,6 +30,7 @@ datasets:
 # Generator model settings
 network_g:
   type: rcan
+  unshuffle_mod: true # has no effect on scales larger than 2. for scales 1 and 2, setting to true speeds up the model and reduces vram usage significantly, but reduces quality.
 
 ############################
 # Pretrain and Resume Paths

options/train/RCAN/RCAN_OTF_bicubic_ms_ssim_l1_fromscratch.yml

@@ -110,6 +110,7 @@ datasets:
 # Generator model settings
 network_g:
   type: rcan
+  unshuffle_mod: true # has no effect on scales larger than 2. for scales 1 and 2, setting to true speeds up the model and reduces vram usage significantly, but reduces quality.
 
 #########################################################################################
 # Pretrain and Resume Paths

options/train/RCAN/RCAN_OTF_finetune.yml

@@ -118,6 +118,7 @@ datasets:
 # Generator model settings
 network_g:
   type: rcan
+  unshuffle_mod: true # has no effect on scales larger than 2. for scales 1 and 2, setting to true speeds up the model and reduces vram usage significantly, but reduces quality.
 
 # Discriminator model settings
 network_d:

options/train/RCAN/RCAN_OTF_fromscratch.yml

@@ -118,6 +118,7 @@ datasets:
 # Generator model settings
 network_g:
   type: rcan
+  unshuffle_mod: true # has no effect on scales larger than 2. for scales 1 and 2, setting to true speeds up the model and reduces vram usage significantly, but reduces quality.
 
 #########################################################################################
 # Pretrain and Resume Paths

options/train/RCAN/RCAN_finetune.yml

@@ -63,6 +63,7 @@ datasets:
 # Generator model settings
 network_g:
   type: rcan
+  unshuffle_mod: true # has no effect on scales larger than 2. for scales 1 and 2, setting to true speeds up the model and reduces vram usage significantly, but reduces quality.
 
 # Discriminator model settings
 network_d:

options/train/RCAN/RCAN_fromscratch.yml

@@ -63,6 +63,7 @@ datasets:
 # Generator model settings
 network_g:
   type: rcan
+  unshuffle_mod: true # has no effect on scales larger than 2. for scales 1 and 2, setting to true speeds up the model and reduces vram usage significantly, but reduces quality.
 
 #########################################################################################
 # Pretrain and Resume Paths

scripts/options/generate_default_options.py

@@ -229,7 +229,6 @@ def final_template(
             "upsampler": "pixelshuffle  # pixelshuffle, nearest+conv, dysample (best on even number scales, does not support dynamic ONNX)"
         },
     },
-    {"names": ["RCAN"], "scales": ALL_SCALES},
     {"names": ["Swin2SR_L", "Swin2SR_M", "Swin2SR_S"], "scales": ALL_SCALES},
     {
         "names": ["MoESR2"],
@@ -239,7 +238,13 @@ def final_template(
             "upsampler": "pixelshuffledirect  # conv, pixelshuffledirect, pixelshuffle, nearest+conv, dysample (best on even number scales, does not support dynamic ONNX)",
         },
     },
-    {"names": ["RCAN"], "scales": ALL_SCALES},
+    {
+        "names": ["RCAN"],
+        "scales": ALL_SCALES,
+        "extras": {
+            "unshuffle_mod": "true # Has no effect on scales larger than 2. For scales 1 and 2, setting to true speeds up the model and reduces VRAM usage significantly, but reduces quality."
+        },
+    },
     {"names": ["RTMoSR", "RTMoSR_L", "RTMoSR_UL"], "scales": ALL_SCALES},
     {
         "names": ["GRL_B", "GRL_S", "GRL_T"],

traiNNer/archs/rcan_arch.py

@@ -257,7 +257,7 @@ def __init__(
         reduction: int = 16,
         res_scale: float = 1,
         act_mode: str = "relu",
-        unshuffle_mod: bool = False,
+        unshuffle_mod: bool = True,
         conv: Callable[..., nn.Conv2d] = default_conv,
     ) -> None:
         super().__init__()
@@ -334,98 +334,4 @@ def forward(self, x: Tensor) -> Tensor:
 
         x = self.tail(res)
         x = self.add_mean(x)
-        out = (x / self.rgb_range)[:, :, : h * self.scale, : w * self.scale]
-        return out
-
-
-# @ARCH_REGISTRY.register()
-# def rcan_rg20(
-#     scale: int = 4,
-#     n_resgroups: int = 20,
-#     n_resblocks: int = 20,
-#     n_feats: int = 64,
-#     n_colors: int = 3,
-#     rgb_range: int = 255,
-#     norm: bool = False,
-#     kernel_size: int = 3,
-#     reduction: int = 16,
-#     res_scale: float = 1,
-#     act_mode: str = "relu",
-#     conv: Callable[..., nn.Conv2d] = default_conv,
-# ) -> RCAN:
-#     return RCAN(
-#         scale=scale,
-#         n_resgroups=n_resgroups,
-#         n_resblocks=n_resblocks,
-#         n_feats=n_feats,
-#         n_colors=n_colors,
-#         rgb_range=rgb_range,
-#         norm=norm,
-#         kernel_size=kernel_size,
-#         reduction=reduction,
-#         res_scale=res_scale,
-#         act_mode=act_mode,
-#         conv=conv,
-#     )
-
-
-# @ARCH_REGISTRY.register()
-# def rcan_rb40(
-#     scale: int = 4,
-#     n_resgroups: int = 10,
-#     n_resblocks: int = 40,
-#     n_feats: int = 64,
-#     n_colors: int = 3,
-#     rgb_range: int = 255,
-#     norm: bool = False,
-#     kernel_size: int = 3,
-#     reduction: int = 16,
-#     res_scale: float = 1,
-#     act_mode: str = "relu",
-#     conv: Callable[..., nn.Conv2d] = default_conv,
-# ) -> RCAN:
-#     return RCAN(
-#         scale=scale,
-#         n_resgroups=n_resgroups,
-#         n_resblocks=n_resblocks,
-#         n_feats=n_feats,
-#         n_colors=n_colors,
-#         rgb_range=rgb_range,
-#         norm=norm,
-#         kernel_size=kernel_size,
-#         reduction=reduction,
-#         res_scale=res_scale,
-#         act_mode=act_mode,
-#         conv=conv,
-#     )
-
-
-# @ARCH_REGISTRY.register()
-# def rcan_nf128(
-#     scale: int = 4,
-#     n_resgroups: int = 10,
-#     n_resblocks: int = 20,
-#     n_feats: int = 128,
-#     n_colors: int = 3,
-#     rgb_range: int = 255,
-#     norm: bool = False,
-#     kernel_size: int = 3,
-#     reduction: int = 16,
-#     res_scale: float = 1,
-#     act_mode: str = "relu",
-#     conv: Callable[..., nn.Conv2d] = default_conv,
-# ) -> RCAN:
-#     return RCAN(
-#         scale=scale,
-#         n_resgroups=n_resgroups,
-#         n_resblocks=n_resblocks,
-#         n_feats=n_feats,
-#         n_colors=n_colors,
-#         rgb_range=rgb_range,
-#         norm=norm,
-#         kernel_size=kernel_size,
-#         reduction=reduction,
-#         res_scale=res_scale,
-#         act_mode=act_mode,
-#         conv=conv,
-#     )
+        return (x / self.rgb_range)[:, :, : h * self.scale, : w * self.scale]