search

AarohiSingla / Mask-R-CNN-using-Tensorflow2

Instance Segmentation
19 stars 12 forks source link

Issue with the lamda function when training with coustom dataset on mask-rcnn #3

Open kumbarisagar3011 opened 2 weeks ago

kumbarisagar3011 commented 2 weeks ago

Traceback (most recent call last): File "D:\Local Disk E\Project-mask-rcnn\Mask_RCNN\custom.py", line 238, in model = modellib.MaskRCNN(mode="training", config=config, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Local Disk E\Project-mask-rcnn\Mask_RCNN\mrcnn\model.py", line 1838, in init self.keras_model = self.build(mode=mode, config=config) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\Local Disk E\Project-mask-rcnn\Mask_RCNN\mrcnn\model.py", line 1876, in build gt_boxes = KL.Lambda(lambda x: norm_boxes_graph( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "d:\Local Disk E\Project-mask-rcnn\mask-rcnn\Lib\site-packages\keras\src\utils\traceback_utils.py", line 122, in erroler raise e.with_traceback(filtered_tb) from None File "d:\Local Disk E\Project-mask-rcnn\mask-rcnn\Lib\site-packages\keras\src\layers\core\lambda_layer.py", line 95, in cooutput_shape raise NotImplementedError( NotImplementedError: Exception encountered when calling Lambda.call().

We could not automatically infer the shape of the Lambda's output. Please specify the output_shape argument for this Lambda layer.

Arguments received by Lambda.call(): • args=('<KerasTensor shape=(None, None, 4), dtype=float32, sparse=None, name=input_gt_boxes>',) • kwargs={'mask': 'None'}

what to do to get rid of this error?

TXWISSRX commented 6 days ago

me too still not solved