[Fix] Prevent Possible Issues Caused by 0-D Tensor (#61)

paddlers/datasets/voc.py

@@ -289,7 +289,8 @@ class VOCDetDataset(BaseDataset):
                     self.num_max_boxes = max(self.num_max_boxes, len(objs))
 
         if not ct:
-            logging.error("No voc record found in %s ." % (file_list), exit=True)
+            logging.error(
+                "No voc record found in %s ." % (file_list), exit=True)
         self.pos_num = len(self.file_list)
         if self.allow_empty and neg_file_list:
             self.file_list += self._sample_empty(neg_file_list)

paddlers/models/ppcls/arch/backbone/model_zoo/gvt.py

@@ -322,8 +322,7 @@ class PyramidVisionTransformer(nn.Layer):
             self.pos_drops.append(nn.Dropout(p=drop_rate))
 
         dpr = [
-            x.numpy()[0]
-            for x in paddle.linspace(0, drop_path_rate, sum(depths))
+            float(x) for x in paddle.linspace(0, drop_path_rate, sum(depths))
         ]  # stochastic depth decay rule
 
         cur = 0
@@ -549,8 +548,7 @@ class ALTGVT(PCPVT):
         self.wss = wss
         # transformer encoder
         dpr = [
-            x.numpy()[0]
-            for x in paddle.linspace(0, drop_path_rate, sum(depths))
+            float(x) for x in paddle.linspace(0, drop_path_rate, sum(depths))
         ]  # stochastic depth decay rule
         cur = 0
         self.blocks = nn.LayerList()

paddlers/models/ppcls/engine/evaluation/classification.py

@@ -72,8 +72,8 @@ def classification_eval(engine, epoch_id=0):
                     for key in loss_dict:
                         if key not in output_info:
                             output_info[key] = AverageMeter(key, '7.5f')
-                        output_info[key].update(loss_dict[key].numpy()[0],
-                                                batch_size)
+                        output_info[key].update(
+                            float(loss_dict[key]), batch_size)
         else:
             out = engine.model(batch[0])
             # calc loss
@@ -82,8 +82,7 @@ def classification_eval(engine, epoch_id=0):
                 for key in loss_dict:
                     if key not in output_info:
                         output_info[key] = AverageMeter(key, '7.5f')
-                    output_info[key].update(loss_dict[key].numpy()[0],
-                                            batch_size)
+                    output_info[key].update(float(loss_dict[key]), batch_size)
 
         # just for DistributedBatchSampler issue: repeat sampling
         current_samples = batch_size * paddle.distributed.get_world_size()
@@ -132,8 +131,8 @@ def classification_eval(engine, epoch_id=0):
                 if key not in output_info:
                     output_info[key] = AverageMeter(key, '7.5f')
 
-                output_info[key].update(metric_dict[key].numpy()[0],
-                                        current_samples)
+                output_info[key].update(
+                    float(metric_dict[key]), current_samples)
 
         time_info["batch_cost"].update(time.time() - tic)
 

paddlers/models/ppcls/engine/train/utils.py

@@ -25,8 +25,7 @@ def update_metric(trainer, out, batch, batch_size):
         for key in metric_dict:
             if key not in trainer.output_info:
                 trainer.output_info[key] = AverageMeter(key, '7.5f')
-            trainer.output_info[key].update(metric_dict[key].numpy()[0],
-                                            batch_size)
+            trainer.output_info[key].update(float(metric_dict[key]), batch_size)
 
 
 def update_loss(trainer, loss_dict, batch_size):
@@ -34,7 +33,7 @@ def update_loss(trainer, loss_dict, batch_size):
     for key in loss_dict:
         if key not in trainer.output_info:
             trainer.output_info[key] = AverageMeter(key, '7.5f')
-        trainer.output_info[key].update(loss_dict[key].numpy()[0], batch_size)
+        trainer.output_info[key].update(float(loss_dict[key]), batch_size)
 
 
 def log_info(trainer, batch_size, epoch_id, iter_id):

paddlers/models/ppcls/metric/metrics.py

@@ -81,7 +81,7 @@ class mAP(nn.Layer):
         #calc map
         precision_mask = paddle.multiply(equal_flag, precision)
         ap = paddle.sum(precision_mask, axis=1) / paddle.sum(equal_flag, axis=1)
-        metric_dict["mAP"] = paddle.mean(ap).numpy()[0]
+        metric_dict["mAP"] = float(paddle.mean(ap))
         return metric_dict
 
 
@@ -124,7 +124,7 @@ class mINP(nn.Layer):
         hard_index = paddle.argmax(auxilary, axis=1).astype("float32")
         all_INP = paddle.divide(paddle.sum(equal_flag, axis=1), hard_index)
         mINP = paddle.mean(all_INP)
-        metric_dict["mINP"] = mINP.numpy()[0]
+        metric_dict["mINP"] = float(mINP)
         return metric_dict
 
 

paddlers/models/ppseg/core/train.py

@@ -231,7 +231,7 @@ def train(model,
             train_profiler.add_profiler_step(profiler_options)
 
             model.clear_gradients()
-            avg_loss += loss.numpy()[0]
+            avg_loss += float(loss)
             if not avg_loss_list:
                 avg_loss_list = [l.numpy() for l in loss_list]
             else:

paddlers/models/ppseg/models/losses/ohem_cross_entropy_loss.py

@@ -77,7 +77,7 @@ class OhemCrossEntropyLoss(nn.Layer):
             if self.min_kept > 0:
                 index = prob.argsort()
                 threshold_index = index[min(len(index), self.min_kept) - 1]
-                threshold_index = int(threshold_index.numpy()[0])
+                threshold_index = int(threshold_index)
                 if prob[threshold_index] > self.thresh:
                     threshold = prob[threshold_index]
                 kept_mask = (prob < threshold).astype('int64')

paddlers/models/ppseg/models/losses/ohem_edge_attention_loss.py

@@ -93,7 +93,7 @@ class OhemEdgeAttentionLoss(nn.Layer):
             if self.min_kept > 0:
                 index = prob.argsort()
                 threshold_index = index[min(len(index), self.min_kept) - 1]
-                threshold_index = int(threshold_index.numpy()[0])
+                threshold_index = int(threshold_index)
                 if prob[threshold_index] > self.thresh:
                     threshold = prob[threshold_index]
                 kept_mask = (prob < threshold).astype('int64')