Add files via upload

lib_v5/vr_network/model_param_init.py

@@ -1,36 +1,15 @@
 import json
-import pathlib
 
 default_param = {}
-default_param['bins'] = 768
+default_param['bins'] = -1
-default_param['unstable_bins'] = 9 # training only
+default_param['unstable_bins'] = -1 # training only
-default_param['reduction_bins'] = 762 # training only
+default_param['stable_bins'] = -1 # training only
 default_param['sr'] = 44100
-default_param['pre_filter_start'] = 757
+default_param['pre_filter_start'] = -1
-default_param['pre_filter_stop'] = 768
+default_param['pre_filter_stop'] = -1
 default_param['band'] = {}
 
-
+N_BINS = 'n_bins'
-default_param['band'][1] = {
-    'sr': 11025,
-    'hl': 128,
-    'n_fft': 960,
-    'crop_start': 0,
-    'crop_stop': 245,
-    'lpf_start': 61, # inference only
-    'res_type': 'polyphase'
-}
-
-default_param['band'][2] = {
-    'sr': 44100,
-    'hl': 512,
-    'n_fft': 1536,
-    'crop_start': 24,
-    'crop_stop': 547,
-    'hpf_start': 81, # inference only
-    'res_type': 'sinc_best'
-}
-
 
 def int_keys(d):
     r = {}
@@ -40,20 +19,14 @@ def int_keys(d):
         r[k] = v
     return r
     
-
 class ModelParameters(object):
     def __init__(self, config_path=''):
-        if '.pth' == pathlib.Path(config_path).suffix:
+        with open(config_path, 'r') as f:
-            import zipfile
-            
-            with zipfile.ZipFile(config_path, 'r') as zip:
-                self.param = json.loads(zip.read('param.json'), object_pairs_hook=int_keys)
-        elif '.json' == pathlib.Path(config_path).suffix:
-            with open(config_path, 'r') as f:
                 self.param = json.loads(f.read(), object_pairs_hook=int_keys)
-        else:
+                
-            self.param = default_param
-            
         for k in ['mid_side', 'mid_side_b', 'mid_side_b2', 'stereo_w', 'stereo_n', 'reverse']:
             if not k in self.param:
-                self.param[k] = False
+                self.param[k] = False
+                
+        if N_BINS in self.param:
+            self.param['bins'] = self.param[N_BINS]

lib_v5/vr_network/modelparams/4band_v3_sn.json

@@ -0,0 +1,55 @@
+{
+	"n_bins": 672,
+	"unstable_bins": 8,
+	"stable_bins": 530,
+	"band": {
+		"1": {
+			"sr": 7350,
+			"hl": 80,
+			"n_fft": 640,
+			"crop_start": 0,
+			"crop_stop": 85,
+			"lpf_start": 25,
+			"lpf_stop": 53,
+			"res_type": "polyphase"
+		},
+		"2": {
+			"sr": 7350,
+			"hl": 80,
+			"n_fft": 320,
+			"crop_start": 4,
+			"crop_stop": 87,
+			"hpf_start": 25,
+			"hpf_stop": 12,
+			"lpf_start": 31,
+			"lpf_stop": 62,
+			"res_type": "polyphase"
+		},
+		"3": {
+			"sr": 14700,
+			"hl": 160,
+			"n_fft": 512,
+			"crop_start": 17,
+			"crop_stop": 216,
+			"hpf_start": 48,
+			"hpf_stop": 24,
+			"lpf_start": 139,
+			"lpf_stop": 210,
+			"res_type": "polyphase"
+		},
+		"4": {
+			"sr": 44100,
+			"hl": 480,
+			"n_fft": 960,
+			"crop_start": 78,
+			"crop_stop": 383,
+			"hpf_start": 130,
+			"hpf_stop": 86,
+			"convert_channels": "stereo_n",
+			"res_type": "kaiser_fast"
+		}
+	},
+	"sr": 44100,
+	"pre_filter_start": 668,
+	"pre_filter_stop": 672
+}

lib_v5/vr_network/nets_new.py

@@ -40,26 +40,26 @@ class BaseNet(nn.Module):
 
 class CascadedNet(nn.Module):
 
-    def __init__(self, n_fft, nn_arch_size, nout=32, nout_lstm=128):
+    def __init__(self, n_fft, nn_arch_size=51000, nout=32, nout_lstm=128):
         super(CascadedNet, self).__init__()
-
         self.max_bin = n_fft // 2
         self.output_bin = n_fft // 2 + 1
         self.nin_lstm = self.max_bin // 2
         self.offset = 64
         nout = 64 if nn_arch_size == 218409 else nout
 
+        #print(nout, nout_lstm, n_fft)
+
         self.stg1_low_band_net = nn.Sequential(
             BaseNet(2, nout // 2, self.nin_lstm // 2, nout_lstm),
             layers.Conv2DBNActiv(nout // 2, nout // 4, 1, 1, 0)
-            )
+        )
-        
         self.stg1_high_band_net = BaseNet(2, nout // 4, self.nin_lstm // 2, nout_lstm // 2)
 
         self.stg2_low_band_net = nn.Sequential(
             BaseNet(nout // 4 + 2, nout, self.nin_lstm // 2, nout_lstm),
             layers.Conv2DBNActiv(nout, nout // 2, 1, 1, 0)
-            )
+        )
         self.stg2_high_band_net = BaseNet(nout // 4 + 2, nout // 2, self.nin_lstm // 2, nout_lstm // 2)
 
         self.stg3_full_band_net = BaseNet(3 * nout // 4 + 2, nout, self.nin_lstm, nout_lstm)