change tensorshape

paddlepalm/backbone/bert.py

@@ -52,10 +52,10 @@ class Model(backbone):
 
     @property
     def inputs_attr(self):
-        return {"token_ids": [[-1, -1, 1], 'int64'],
-                "position_ids": [[-1, -1, 1], 'int64'],
-                "segment_ids": [[-1, -1, 1], 'int64'],
-                "input_mask": [[-1, -1, 1], 'float32']}
+        return {"token_ids": [[-1, -1], 'int64'],
+                "position_ids": [[-1, -1], 'int64'],
+                "segment_ids": [[-1, -1], 'int64'],
+                "input_mask": [[-1, -1], 'float32']}
 
     @property
     def outputs_attr(self):

paddlepalm/backbone/ernie.py

@@ -62,11 +62,11 @@ class Model(backbone):
 
     @property
     def inputs_attr(self):
-        return {"token_ids": [[-1, -1, 1], 'int64'],
-                "position_ids": [[-1, -1, 1], 'int64'],
-                "segment_ids": [[-1, -1, 1], 'int64'],
-                "input_mask": [[-1, -1, 1], 'float32'],
-                "task_ids": [[-1,-1, 1], 'int64']}
+        return {"token_ids": [[-1, -1], 'int64'],
+                "position_ids": [[-1, -1], 'int64'],
+                "segment_ids": [[-1, -1], 'int64'],
+                "input_mask": [[-1, -1], 'float32'],
+                "task_ids": [[-1,-1], 'int64']}
 
     @property
     def outputs_attr(self):

paddlepalm/reader/mlm.py

@@ -60,13 +60,13 @@ class Reader(reader):
 
     @property
     def outputs_attr(self):
-        return {"token_ids": [[-1, -1, 1], 'int64'],
-                "position_ids": [[-1, -1, 1], 'int64'],
-                "segment_ids": [[-1, -1, 1], 'int64'],
-                "input_mask": [[-1, -1, 1], 'float32'],
-                "task_ids": [[-1, -1, 1], 'int64'],
-                "mask_label": [[-1, 1], 'int64'],
-                "mask_pos": [[-1, 1], 'int64'],
+        return {"token_ids": [[-1, -1], 'int64'],
+                "position_ids": [[-1, -1], 'int64'],
+                "segment_ids": [[-1, -1], 'int64'],
+                "input_mask": [[-1, -1], 'float32'],
+                "task_ids": [[-1, -1], 'int64'],
+                "mask_label": [[-1], 'int64'],
+                "mask_pos": [[-1], 'int64'],
                 }
 
 

paddlepalm/reader/utils/batching4bert.py

@@ -67,8 +67,8 @@ def mask(batch_tokens, total_token_num, vocab_size, CLS=1, SEP=2, MASK=3):
                 sent[token_index] = MASK
                 mask_flag = True
                 mask_pos.append(sent_index * max_len + token_index)
-    mask_label = np.array(mask_label).astype("int64").reshape([-1, 1])
-    mask_pos = np.array(mask_pos).astype("int64").reshape([-1, 1])
+    mask_label = np.array(mask_label).astype("int64").reshape([-1])
+    mask_pos = np.array(mask_pos).astype("int64").reshape([-1])
     return batch_tokens, mask_label, mask_pos
 
 
@@ -96,7 +96,7 @@ def prepare_batch_data(insts,
     # or unique id
     for i in range(3, len(insts[0]), 1):
         labels = [inst[i] for inst in insts]
-        labels = np.array(labels).astype("int64").reshape([-1, 1])
+        labels = np.array(labels).astype("int64").reshape([-1])
         labels_list.append(labels)
     # First step: do mask without padding
     if mask_id >= 0:
@@ -154,14 +154,14 @@ def pad_batch_data(insts,
     inst_data = np.array([
         list(inst) + list([pad_idx] * (max_len - len(inst))) for inst in insts
     ])
-    return_list += [inst_data.astype("int64").reshape([-1, max_len, 1])]
+    return_list += [inst_data.astype("int64").reshape([-1, max_len])]
     # position data
     if return_pos:
         inst_pos = np.array([
             list(range(0, len(inst))) + [pad_idx] * (max_len - len(inst))
             for inst in insts
         ])
-        return_list += [inst_pos.astype("int64").reshape([-1, max_len, 1])]
+        return_list += [inst_pos.astype("int64").reshape([-1, max_len])]
     if return_input_mask:
         # This is used to avoid attention on paddings.
         input_mask_data = np.array([[1] * len(inst) + [0] *

paddlepalm/reader/utils/batching4ernie.py

@@ -113,8 +113,8 @@ def mask(batch_tokens,
 
         pre_sent_len = len(sent)
 
-    mask_label = np.array(mask_label).astype("int64").reshape([-1, 1])
-    mask_pos = np.array(mask_pos).astype("int64").reshape([-1, 1])
+    mask_label = np.array(mask_label).astype("int64").reshape([-1])
+    mask_pos = np.array(mask_pos).astype("int64").reshape([-1])
     return batch_tokens, mask_label, mask_pos
 
 
@@ -136,7 +136,7 @@ def pad_batch_data(insts,
 
     inst_data = np.array(
         [inst + list([pad_idx] * (max_len - len(inst))) for inst in insts])
-    return_list += [inst_data.astype("int64").reshape([-1, max_len, 1])]
+    return_list += [inst_data.astype("int64").reshape([-1, max_len])]
 
     # position data
     if return_pos:
@@ -145,7 +145,7 @@ def pad_batch_data(insts,
             for inst in insts
         ])
 
-        return_list += [inst_pos.astype("int64").reshape([-1, max_len, 1])]
+        return_list += [inst_pos.astype("int64").reshape([-1, max_len])]
 
     if return_input_mask:
         # This is used to avoid attention on paddings.
@@ -165,7 +165,7 @@ def pad_batch_data(insts,
 
     if return_seq_lens:
         seq_lens = np.array([len(inst) for inst in insts])
-        return_list += [seq_lens.astype("int64").reshape([-1, 1])]
+        return_list += [seq_lens.astype("int64").reshape([-1])]
 
     return return_list if len(return_list) > 1 else return_list[0]
 

paddlepalm/reader/utils/mlm_batching.py

@@ -67,8 +67,8 @@ def mask(batch_tokens, total_token_num, vocab_size, CLS=1, SEP=2, MASK=3):
                 sent[token_index] = MASK
                 mask_flag = True
                 mask_pos.append(sent_index * max_len + token_index)
-    mask_label = np.array(mask_label).astype("int64").reshape([-1, 1])
-    mask_pos = np.array(mask_pos).astype("int64").reshape([-1, 1])
+    mask_label = np.array(mask_label).astype("int64").reshape([-1])
+    mask_pos = np.array(mask_pos).astype("int64").reshape([-1])
     return batch_tokens, mask_label, mask_pos
 
 
@@ -147,14 +147,14 @@ def pad_batch_data(insts,
     inst_data = np.array([
         list(inst) + list([pad_idx] * (max_len - len(inst))) for inst in insts
     ])
-    return_list += [inst_data.astype("int64").reshape([-1, max_len, 1])]
+    return_list += [inst_data.astype("int64").reshape([-1, max_len])]
     # position data
     if return_pos:
         inst_pos = np.array([
             list(range(0, len(inst))) + [pad_idx] * (max_len - len(inst))
             for inst in insts
         ])
-        return_list += [inst_pos.astype("int64").reshape([-1, max_len, 1])]
+        return_list += [inst_pos.astype("int64").reshape([-1, max_len])]
     if return_input_mask:
         # This is used to avoid attention on paddings.
         input_mask_data = np.array([[1] * len(inst) + [0] *

paddlepalm/reader/utils/reader4ernie.py

@@ -479,17 +479,17 @@ class ClassifyReader(BaseReader):
             batch_labels = [record.label_id for record in batch_records]
             if self.is_classify:
                 batch_labels = np.array(batch_labels).astype("int64").reshape(
-                    [-1, 1])
+                    [-1])
             elif self.is_regression:
                 batch_labels = np.array(batch_labels).astype("float32").reshape(
-                    [-1, 1])
+                    [-1])
 
             if batch_records[0].qid:
                 batch_qids = [record.qid for record in batch_records]
                 batch_qids = np.array(batch_qids).astype("int64").reshape(
-                    [-1, 1])
+                    [-1])
             else:
-                batch_qids = np.array([]).astype("int64").reshape([-1, 1])
+                batch_qids = np.array([]).astype("int64").reshape([-1])
 
         # padding
         padded_token_ids, input_mask = pad_batch_data(
@@ -908,15 +908,15 @@ class MRCReader(BaseReader):
                 record.end_position for record in batch_records
             ]
             batch_start_position = np.array(batch_start_position).astype(
-                "int64").reshape([-1, 1])
+                "int64").reshape([-1])
             batch_end_position = np.array(batch_end_position).astype(
-                "int64").reshape([-1, 1])
+                "int64").reshape([-1])
 
         else:
             batch_size = len(batch_token_ids)
             batch_start_position = np.zeros(
-                shape=[batch_size, 1], dtype="int64")
-            batch_end_position = np.zeros(shape=[batch_size, 1], dtype="int64")
+                shape=[batch_size], dtype="int64")
+            batch_end_position = np.zeros(shape=[batch_size], dtype="int64")
 
         batch_unique_ids = [record.unique_id for record in batch_records]
         batch_unique_ids = np.array(batch_unique_ids).astype("int64").reshape(

paddlepalm/task_paradigm/cls.py

@@ -43,7 +43,7 @@ class TaskParadigm(task_paradigm):
     @property
     def inputs_attrs(self):
         if self._is_training:
-            reader = {"label_ids": [[-1, 1], 'int64']}
+            reader = {"label_ids": [[-1], 'int64']}
         else:
             reader = {}
         bb = {"sentence_embedding": [[-1, self._hidden_size], 'float32']}

paddlepalm/task_paradigm/match.py

@@ -44,7 +44,7 @@ class TaskParadigm(task_paradigm):
     @property
     def inputs_attrs(self):
         if self._is_training:
-            reader = {"label_ids": [[-1, 1], 'int64']}
+            reader = {"label_ids": [[-1], 'int64']}
         else:
             reader = {}
         bb = {"sentence_pair_embedding": [[-1, self._hidden_size], 'float32']}

paddlepalm/task_paradigm/mlm.py

@@ -33,8 +33,8 @@ class TaskParadigm(task_paradigm):
     @property
     def inputs_attrs(self):
         reader = {
-            "mask_label": [[-1, 1], 'int64'],
-            "mask_pos": [[-1, 1], 'int64']}
+            "mask_label": [[-1], 'int64'],
+            "mask_pos": [[-1], 'int64']}
         if not self._is_training:
             del reader['mask_label']
             del reader['batchsize_x_seqlen']

paddlepalm/task_paradigm/mrc.py

@@ -49,11 +49,11 @@ class TaskParadigm(task_paradigm):
     @property
     def inputs_attrs(self):
         if self._is_training:
-            reader = {"start_positions": [[-1, 1], 'int64'],
-                      "end_positions": [[-1, 1], 'int64'],
+            reader = {"start_positions": [[-1], 'int64'],
+                      "end_positions": [[-1], 'int64'],
                       }
         else:
-            reader = {'unique_ids': [[-1, 1], 'int64']}
+            reader = {'unique_ids': [[-1], 'int64']}
         bb = {"encoder_outputs": [[-1, -1, self._hidden_size], 'float32']}
         return {'reader': reader, 'backbone': bb}
         
@@ -68,9 +68,9 @@ class TaskParadigm(task_paradigm):
         if self._is_training:
             return {'loss': [[1], 'float32']}
         else:
-            return {'start_logits': [[-1, -1, 1], 'float32'],
-                    'end_logits': [[-1, -1, 1], 'float32'],
-                    'unique_ids': [[-1, 1], 'int64']}
+            return {'start_logits': [[-1, -1], 'float32'],
+                    'end_logits': [[-1, -1], 'float32'],
+                    'unique_ids': [[-1], 'int64']}
 
 
     def build(self, inputs, scope_name=""):