English CRNN v2 architecture

english/shobdo_english.py

@@ -4,7 +4,7 @@ import torch.nn.functional as F
 class ConvBnRelu(nn.Module):
     def __init__(self, i, o, k=3, s=1, p=1):
         super().__init__()
-        self.b = nn.Sequential(nn.Conv2d(i,o,k,s,p,bias=False),nn.BatchNorm2d(o),nn.ReLU(inplace=True))
+        self.b = nn.Sequential(nn.Conv2d(i,o,k,s,p,bias=False),nn.BatchNorm2d(o),nn.ReLU(True))
     def forward(self, x): return self.b(x)
 
 class LightCNN(nn.Module):
@@ -25,11 +25,10 @@ class BiLSTMBlock(nn.Module):
         super().__init__()
         self.rnn=nn.LSTM(i,h,bidirectional=True,batch_first=True)
         self.fc=nn.Linear(h*2,o)
-    def forward(self, x):
-        o,_=self.rnn(x); return self.fc(o)
+    def forward(self, x): o,_=self.rnn(x); return self.fc(o)
 
 class Model(nn.Module):
-    def __init__(self, input_channel=1, output_channel=256, hidden_size=256, num_class=73):
+    def __init__(self, input_channel=1, output_channel=256, hidden_size=256, num_class=76):
         super().__init__()
         self.cnn=LightCNN()
         self.rnn=nn.Sequential(BiLSTMBlock(256,hidden_size,hidden_size),
@@ -37,4 +36,4 @@ class Model(nn.Module):
     def forward(self, x):
         f=self.cnn(x).permute(0,2,1)
         o=self.rnn(f).permute(1,0,2)
-        return F.log_softmax(o,dim=2)
+        return F.log_softmax(o,dim=2)