Merge pull request #2067 from victorca25/esrgan_mod

update ESRGAN architecture and model to support all ESRGAN models

modules/esrgan_model.py

@@ -11,62 +11,109 @@
 from modules.shared import opts
 
 
-def fix_model_layers(crt_model, pretrained_net):
-    # this code is adapted from https://github.com/xinntao/ESRGAN
-    if 'conv_first.weight' in pretrained_net:
-        return pretrained_net
-
-    if 'model.0.weight' not in pretrained_net:
-        is_realesrgan = "params_ema" in pretrained_net and 'body.0.rdb1.conv1.weight' in pretrained_net["params_ema"]
-        if is_realesrgan:
-            raise Exception("The file is a RealESRGAN model, it can't be used as a ESRGAN model.")
-        else:
-            raise Exception("The file is not a ESRGAN model.")
 
-    crt_net = crt_model.state_dict()
-    load_net_clean = {}
-    for k, v in pretrained_net.items():
-        if k.startswith('module.'):
-            load_net_clean[k[7:]] = v
-        else:
-            load_net_clean[k] = v
-    pretrained_net = load_net_clean
-
-    tbd = []
-    for k, v in crt_net.items():
-        tbd.append(k)
-
-    # directly copy
-    for k, v in crt_net.items():
-        if k in pretrained_net and pretrained_net[k].size() == v.size():
-            crt_net[k] = pretrained_net[k]
-            tbd.remove(k)
-
-    crt_net['conv_first.weight'] = pretrained_net['model.0.weight']
-    crt_net['conv_first.bias'] = pretrained_net['model.0.bias']
-
-    for k in tbd.copy():
-        if 'RDB' in k:
-            ori_k = k.replace('RRDB_trunk.', 'model.1.sub.')
-            if '.weight' in k:
-                ori_k = ori_k.replace('.weight', '.0.weight')
-            elif '.bias' in k:
-                ori_k = ori_k.replace('.bias', '.0.bias')
-            crt_net[k] = pretrained_net[ori_k]
-            tbd.remove(k)
-
-    crt_net['trunk_conv.weight'] = pretrained_net['model.1.sub.23.weight']
-    crt_net['trunk_conv.bias'] = pretrained_net['model.1.sub.23.bias']
-    crt_net['upconv1.weight'] = pretrained_net['model.3.weight']
-    crt_net['upconv1.bias'] = pretrained_net['model.3.bias']
-    crt_net['upconv2.weight'] = pretrained_net['model.6.weight']
-    crt_net['upconv2.bias'] = pretrained_net['model.6.bias']
-    crt_net['HRconv.weight'] = pretrained_net['model.8.weight']
-    crt_net['HRconv.bias'] = pretrained_net['model.8.bias']
-    crt_net['conv_last.weight'] = pretrained_net['model.10.weight']
-    crt_net['conv_last.bias'] = pretrained_net['model.10.bias']
-
-    return crt_net
+def mod2normal(state_dict):
+    # this code is copied from https://github.com/victorca25/iNNfer
+    if 'conv_first.weight' in state_dict:
+        crt_net = {}
+        items = []
+        for k, v in state_dict.items():
+            items.append(k)
+
+        crt_net['model.0.weight'] = state_dict['conv_first.weight']
+        crt_net['model.0.bias'] = state_dict['conv_first.bias']
+
+        for k in items.copy():
+            if 'RDB' in k:
+                ori_k = k.replace('RRDB_trunk.', 'model.1.sub.')
+                if '.weight' in k:
+                    ori_k = ori_k.replace('.weight', '.0.weight')
+                elif '.bias' in k:
+                    ori_k = ori_k.replace('.bias', '.0.bias')
+                crt_net[ori_k] = state_dict[k]
+                items.remove(k)
+
+        crt_net['model.1.sub.23.weight'] = state_dict['trunk_conv.weight']
+        crt_net['model.1.sub.23.bias'] = state_dict['trunk_conv.bias']
+        crt_net['model.3.weight'] = state_dict['upconv1.weight']
+        crt_net['model.3.bias'] = state_dict['upconv1.bias']
+        crt_net['model.6.weight'] = state_dict['upconv2.weight']
+        crt_net['model.6.bias'] = state_dict['upconv2.bias']
+        crt_net['model.8.weight'] = state_dict['HRconv.weight']
+        crt_net['model.8.bias'] = state_dict['HRconv.bias']
+        crt_net['model.10.weight'] = state_dict['conv_last.weight']
+        crt_net['model.10.bias'] = state_dict['conv_last.bias']
+        state_dict = crt_net
+    return state_dict
+
+
+def resrgan2normal(state_dict, nb=23):
+    # this code is copied from https://github.com/victorca25/iNNfer
+    if "conv_first.weight" in state_dict and "body.0.rdb1.conv1.weight" in state_dict:
+        crt_net = {}
+        items = []
+        for k, v in state_dict.items():
+            items.append(k)
+
+        crt_net['model.0.weight'] = state_dict['conv_first.weight']
+        crt_net['model.0.bias'] = state_dict['conv_first.bias']
+
+        for k in items.copy():
+            if "rdb" in k:
+                ori_k = k.replace('body.', 'model.1.sub.')
+                ori_k = ori_k.replace('.rdb', '.RDB')
+                if '.weight' in k:
+                    ori_k = ori_k.replace('.weight', '.0.weight')
+                elif '.bias' in k:
+                    ori_k = ori_k.replace('.bias', '.0.bias')
+                crt_net[ori_k] = state_dict[k]
+                items.remove(k)
+
+        crt_net[f'model.1.sub.{nb}.weight'] = state_dict['conv_body.weight']
+        crt_net[f'model.1.sub.{nb}.bias'] = state_dict['conv_body.bias']
+        crt_net['model.3.weight'] = state_dict['conv_up1.weight']
+        crt_net['model.3.bias'] = state_dict['conv_up1.bias']
+        crt_net['model.6.weight'] = state_dict['conv_up2.weight']
+        crt_net['model.6.bias'] = state_dict['conv_up2.bias']
+        crt_net['model.8.weight'] = state_dict['conv_hr.weight']
+        crt_net['model.8.bias'] = state_dict['conv_hr.bias']
+        crt_net['model.10.weight'] = state_dict['conv_last.weight']
+        crt_net['model.10.bias'] = state_dict['conv_last.bias']
+        state_dict = crt_net
+    return state_dict
+
+
+def infer_params(state_dict):
+    # this code is copied from https://github.com/victorca25/iNNfer
+    scale2x = 0
+    scalemin = 6
+    n_uplayer = 0
+    plus = False
+
+    for block in list(state_dict):
+        parts = block.split(".")
+        n_parts = len(parts)
+        if n_parts == 5 and parts[2] == "sub":
+            nb = int(parts[3])
+        elif n_parts == 3:
+            part_num = int(parts[1])
+            if (part_num > scalemin
+                and parts[0] == "model"
+                and parts[2] == "weight"):
+                scale2x += 1
+            if part_num > n_uplayer:
+                n_uplayer = part_num
+                out_nc = state_dict[block].shape[0]
+        if not plus and "conv1x1" in block:
+            plus = True
+
+    nf = state_dict["model.0.weight"].shape[0]
+    in_nc = state_dict["model.0.weight"].shape[1]
+    out_nc = out_nc
+    scale = 2 ** scale2x
+
+    return in_nc, out_nc, nf, nb, plus, scale
+
 
 class UpscalerESRGAN(Upscaler):
     def __init__(self, dirname):
@@ -109,20 +156,39 @@ def load_model(self, path: str):
             print("Unable to load %s from %s" % (self.model_path, filename))
             return None
 
-        pretrained_net = torch.load(filename, map_location='cpu' if devices.device_esrgan.type == 'mps' else None)
-        crt_model = arch.RRDBNet(3, 3, 64, 23, gc=32)
+        state_dict = torch.load(filename, map_location='cpu' if devices.device_esrgan.type == 'mps' else None)
+
+        if "params_ema" in state_dict:
+            state_dict = state_dict["params_ema"]
+        elif "params" in state_dict:
+            state_dict = state_dict["params"]
+            num_conv = 16 if "realesr-animevideov3" in filename else 32
+            model = arch.SRVGGNetCompact(num_in_ch=3, num_out_ch=3, num_feat=64, num_conv=num_conv, upscale=4, act_type='prelu')
+            model.load_state_dict(state_dict)
+            model.eval()
+            return model
+
+        if "body.0.rdb1.conv1.weight" in state_dict and "conv_first.weight" in state_dict:
+            nb = 6 if "RealESRGAN_x4plus_anime_6B" in filename else 23
+            state_dict = resrgan2normal(state_dict, nb)
+        elif "conv_first.weight" in state_dict:
+            state_dict = mod2normal(state_dict)
+        elif "model.0.weight" not in state_dict:
+            raise Exception("The file is not a recognized ESRGAN model.")
+
+        in_nc, out_nc, nf, nb, plus, mscale = infer_params(state_dict)
 
-        pretrained_net = fix_model_layers(crt_model, pretrained_net)
-        crt_model.load_state_dict(pretrained_net)
-        crt_model.eval()
+        model = arch.RRDBNet(in_nc=in_nc, out_nc=out_nc, nf=nf, nb=nb, upscale=mscale, plus=plus)
+        model.load_state_dict(state_dict)
+        model.eval()
 
-        return crt_model
+        return model
 
 
 def upscale_without_tiling(model, img):
     img = np.array(img)
     img = img[:, :, ::-1]
-    img = np.moveaxis(img, 2, 0) / 255
+    img = np.ascontiguousarray(np.transpose(img, (2, 0, 1))) / 255
     img = torch.from_numpy(img).float()
     img = img.unsqueeze(0).to(devices.device_esrgan)
     with torch.no_grad():