Remove unused variables in src.

src/transformers/data/metrics/__init__.py

@@ -19,7 +19,7 @@ try:
     from sklearn.metrics import matthews_corrcoef, f1_score
 
     _has_sklearn = True
-except (AttributeError, ImportError) as e:
+except (AttributeError, ImportError):
     _has_sklearn = False
 
 

src/transformers/modeling_albert.py

@@ -241,8 +241,6 @@ class AlbertAttention(BertSelfAttention):
         context_layer = torch.matmul(attention_probs, value_layer)
 
         context_layer = context_layer.permute(0, 2, 1, 3).contiguous()
-        new_context_layer_shape = context_layer.size()[:-2] + (self.all_head_size,)
-        reshaped_context_layer = context_layer.view(*new_context_layer_shape)
 
         # Should find a better way to do this
         w = (
@@ -334,9 +332,6 @@ class AlbertTransformer(nn.Module):
             # Index of the hidden group
             group_idx = int(i / (self.config.num_hidden_layers / self.config.num_hidden_groups))
 
-            # Index of the layer inside the group
-            layer_idx = int(i - group_idx * layers_per_group)
-
             layer_group_output = self.albert_layer_groups[group_idx](
                 hidden_states,
                 attention_mask,

src/transformers/modeling_t5.py

@@ -629,7 +629,6 @@ class T5Stack(T5PreTrainedModel):
                 all_attentions = all_attentions + (layer_outputs[1],)  # We keep only self-attention weights for now
 
         hidden_states = self.final_layer_norm(hidden_states)
-        layer_output = self.dropout(hidden_states)
 
         # Add last layer
         if self.output_hidden_states:

src/transformers/modeling_tf_pytorch_utils.py

@@ -122,7 +122,7 @@ def load_pytorch_weights_in_tf2_model(tf_model, pt_state_dict, tf_inputs=None, a
         tf_inputs = tf_model.dummy_inputs
 
     if tf_inputs is not None:
-        tfo = tf_model(tf_inputs, training=False)  # Make sure model is built
+        tf_model(tf_inputs, training=False)  # Make sure model is built
 
     # Adapt state dict - TODO remove this and update the AWS weights files instead
     # Convert old format to new format if needed from a PyTorch state_dict
@@ -187,7 +187,7 @@ def load_pytorch_weights_in_tf2_model(tf_model, pt_state_dict, tf_inputs=None, a
     K.batch_set_value(weight_value_tuples)
 
     if tf_inputs is not None:
-        tfo = tf_model(tf_inputs, training=False)  # Make sure restore ops are run
+        tf_model(tf_inputs, training=False)  # Make sure restore ops are run
 
     logger.info("Loaded {:,} parameters in the TF 2.0 model.".format(tf_loaded_numel))
 
@@ -218,7 +218,6 @@ def load_tf2_checkpoint_in_pytorch_model(pt_model, tf_checkpoint_path, tf_inputs
 
     import transformers
 
-    tf_path = os.path.abspath(tf_checkpoint_path)
     logger.info("Loading TensorFlow weights from {}".format(tf_checkpoint_path))
 
     # Instantiate and load the associated TF 2.0 model
@@ -230,7 +229,7 @@ def load_tf2_checkpoint_in_pytorch_model(pt_model, tf_checkpoint_path, tf_inputs
         tf_inputs = tf_model.dummy_inputs
 
     if tf_inputs is not None:
-        tfo = tf_model(tf_inputs, training=False)  # Make sure model is built
+        tf_model(tf_inputs, training=False)  # Make sure model is built
 
     tf_model.load_weights(tf_checkpoint_path, by_name=True)
 

src/transformers/modeling_tf_t5.py

@@ -491,7 +491,6 @@ class TFT5MainLayer(tf.keras.layers.Layer):
                 all_attentions = all_attentions + (layer_outputs[1],)
 
         hidden_states = self.final_layer_norm(hidden_states)
-        layer_output = self.dropout(hidden_states, training=training)
 
         # Add last layer
         if self.output_hidden_states:

src/transformers/modeling_tf_transfo_xl_utilities.py

@@ -118,7 +118,6 @@ class TFAdaptiveSoftmaxMask(tf.keras.layers.Layer):
         hidden, target = inputs
         head_logprob = 0
         if self.n_clusters == 0:
-            softmax_b = tf.get_variable("bias", [self.config.vocab_size], initializer=tf.zeros_initializer())
             output = self._logit(hidden, self.out_layers[0][0], self.out_layers[0][1], self.out_projs[0])
             if target is not None:
                 loss = tf.nn.sparse_softmax_cross_entropy_with_logits(labels=target, logits=output)

src/transformers/modeling_tf_utils.py

@@ -320,7 +320,7 @@ class TFPreTrainedModel(tf.keras.Model):
             # Load from a PyTorch checkpoint
             return load_pytorch_checkpoint_in_tf2_model(model, resolved_archive_file, allow_missing_keys=True)
 
-        ret = model(model.dummy_inputs, training=False)  # build the network with dummy inputs
+        model(model.dummy_inputs, training=False)  # build the network with dummy inputs
 
         assert os.path.isfile(resolved_archive_file), "Error retrieving file {}".format(resolved_archive_file)
         # 'by_name' allow us to do transfer learning by skipping/adding layers
@@ -333,7 +333,7 @@ class TFPreTrainedModel(tf.keras.Model):
                 "If you tried to load a TF 2.0 model from a PyTorch checkpoint, please set from_pt=True. "
             )
 
-        ret = model(model.dummy_inputs, training=False)  # Make sure restore ops are run
+        model(model.dummy_inputs, training=False)  # Make sure restore ops are run
 
         # Check if the models are the same to output loading informations
         with h5py.File(resolved_archive_file, "r") as f:
@@ -515,7 +515,7 @@ class TFSequenceSummary(tf.keras.layers.Layer):
             cls_index = inputs[1] if len(inputs) > 1 else None
             assert len(inputs) <= 2, "Too many inputs."
         else:
-            input_ids = inputs.get("input_ids")
+            hidden_states = inputs.get("hidden_states")
             cls_index = inputs.get("cls_index", None)
 
         if self.summary_type == "last":