Fix E714 flake8 warning (x8).

examples/summarization/modeling_bertabs.py

@@ -519,7 +519,7 @@ class MultiHeadedAttention(nn.Module):
 
         attn = self.softmax(scores)
 
-        if not predefined_graph_1 is None:
+        if predefined_graph_1 is not None:
             attn_masked = attn[:, -1] * predefined_graph_1
             attn_masked = attn_masked / (torch.sum(attn_masked, 2).unsqueeze(2) + 1e-9)
 

templates/adding_a_new_model/modeling_tf_xxx.py

@@ -152,7 +152,7 @@ class TFXxxMainLayer(tf.keras.layers.Layer):
         # attention_probs has shape bsz x n_heads x N x N
         # input head_mask has shape [num_heads] or [num_hidden_layers x num_heads]
         # and head_mask is converted to shape [num_hidden_layers x batch x num_heads x seq_length x seq_length]
-        if not head_mask is None:
+        if head_mask is not None:
             raise NotImplementedError
         else:
             head_mask = [None] * self.num_hidden_layers

transformers/modeling_tf_albert.py

@@ -686,7 +686,7 @@ class TFAlbertModel(TFAlbertPreTrainedModel):
         # attention_probs has shape bsz x n_heads x N x N
         # input head_mask has shape [num_heads] or [num_hidden_layers x num_heads]
         # and head_mask is converted to shape [num_hidden_layers x batch x num_heads x seq_length x seq_length]
-        if not head_mask is None:
+        if head_mask is not None:
             raise NotImplementedError
         else:
             head_mask = [None] * self.num_hidden_layers

transformers/modeling_tf_bert.py

@@ -562,7 +562,7 @@ class TFBertMainLayer(tf.keras.layers.Layer):
         # attention_probs has shape bsz x n_heads x N x N
         # input head_mask has shape [num_heads] or [num_hidden_layers x num_heads]
         # and head_mask is converted to shape [num_hidden_layers x batch x num_heads x seq_length x seq_length]
-        if not head_mask is None:
+        if head_mask is not None:
             raise NotImplementedError
         else:
             head_mask = [None] * self.num_hidden_layers

transformers/modeling_tf_gpt2.py

@@ -311,7 +311,7 @@ class TFGPT2MainLayer(tf.keras.layers.Layer):
         # attention_probs has shape bsz x n_heads x N x N
         # input head_mask has shape [num_heads] or [num_hidden_layers x num_heads]
         # and head_mask is converted to shape [num_hidden_layers x batch x num_heads x seq_length x seq_length]
-        if not head_mask is None:
+        if head_mask is not None:
             raise NotImplementedError
         else:
             head_mask = [None] * self.num_hidden_layers

transformers/modeling_tf_openai.py

@@ -303,7 +303,7 @@ class TFOpenAIGPTMainLayer(tf.keras.layers.Layer):
         # attention_probs has shape bsz x n_heads x N x N
         # input head_mask has shape [num_heads] or [num_hidden_layers x num_heads]
         # and head_mask is converted to shape [num_hidden_layers x batch x num_heads x seq_length x seq_length]
-        if not head_mask is None:
+        if head_mask is not None:
             raise NotImplementedError
         else:
             head_mask = [None] * self.num_hidden_layers

transformers/modeling_tf_t5.py

@@ -456,7 +456,7 @@ class TFT5MainLayer(tf.keras.layers.Layer):
         # attention_probs has shape bsz x n_heads x N x N
         # input head_mask has shape [num_heads] or [num_hidden_layers x num_heads]
         # and head_mask is converted to shape [num_hidden_layers x batch x num_heads x seq_length x seq_length]
-        if not head_mask is None:
+        if head_mask is not None:
             raise NotImplementedError
         else:
             head_mask = [None] * self.num_hidden_layers

transformers/modeling_tf_transfo_xl.py

@@ -554,7 +554,7 @@ class TFTransfoXLMainLayer(tf.keras.layers.Layer):
         # attention_probs has shape bsz x n_heads x N x N
         # input head_mask has shape [num_heads] or [num_hidden_layers x num_heads] (a head_mask for each layer)
         # and head_mask is converted to shape [num_hidden_layers x qlen x klen x bsz x n_head]
-        if not head_mask is None:
+        if head_mask is not None:
             raise NotImplementedError
         else:
             head_mask = [None] * self.n_layer