You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
TypeError: Could not build a TypeSpec for KerasTensor(type_spec=TensorSpec(shape=(None, None, 4), dtype=tf.float32, name=None), name='tf.math.truediv_2/truediv:0', description="created by layer 'tf.math.truediv_2'") of unsupported type <class 'keras.src.engine.keras_tensor.KerasTensor'>.
The text was updated successfully, but these errors were encountered:
anyone who cleared this error
TypeError Traceback (most recent call last)
--> 202 model = MaskRCNN(mode='training', model_dir=DEFAULT_LOGS_DIR, config=config)
203 # load weights (mscoco) and exclude the output layers
204 model.load_weights(COCO_WEIGHTS_PATH, by_name=True, exclude=["mrcnn_class_logits", "mrcnn_bbox_fc", "mrcnn_bbox", "mrcnn_mask"])
3 frames
/usr/local/lib/python3.10/dist-packages/mrcnn/model.py in init(self, mode, config, model_dir)
1830 self.model_dir = model_dir
1831 self.set_log_dir()
-> 1832 self.keras_model = self.build(mode=mode, config=config)
1833
1834 def build(self, mode, config):
/usr/local/lib/python3.10/dist-packages/mrcnn/model.py in build(self, mode, config)
1868 shape=[None, 4], name="input_gt_boxes", dtype=tf.float32)
1869 # Normalize coordinates
-> 1870 gt_boxes = KL.Lambda(lambda x: norm_boxes_graph(
1871 x, K.shape(input_image)[1:3]))(input_gt_boxes)
1872 # 3. GT Masks (zero padded)
/usr/local/lib/python3.10/dist-packages/keras/src/utils/traceback_utils.py in error_handler(*args, **kwargs)
68 # To get the full stack trace, call:
69 #
tf.debugging.disable_traceback_filtering()
---> 70 raise e.with_traceback(filtered_tb) from None
71 finally:
72 del filtered_tb
/usr/local/lib/python3.10/dist-packages/tensorflow/python/framework/type_spec.py in type_spec_from_value(value)
1002 3, "Failed to convert %r to tensor: %s" % (type(value).name, e))
1003
-> 1004 raise TypeError(f"Could not build a TypeSpec for {value} of "
1005 f"unsupported type {type(value)}.")
1006
TypeError: Could not build a TypeSpec for KerasTensor(type_spec=TensorSpec(shape=(None, None, 4), dtype=tf.float32, name=None), name='tf.math.truediv_2/truediv:0', description="created by layer 'tf.math.truediv_2'") of unsupported type <class 'keras.src.engine.keras_tensor.KerasTensor'>.
The text was updated successfully, but these errors were encountered: