Dear Author,
When I am running this part of the code inside Google Colab,
Creating model in Inference mode
import tensorflow as tf
with tf.device(DEVICE):
model = modellib.MaskRCNN(mode="inference", model_dir=MODEL_DIR, config=config)
Loading the last best model which is trained
weights_path = model.find_last()[1]
custom_WEIGHTS_PATH = '/content/drive/MyDrive/car-damage-detection-using-CNN/logs/mask_rcnn_coco.h5'
Load weights
print("Loading weights ", custom_WEIGHTS_PATH)
model.load_weights(custom_WEIGHTS_PATH, by_name=True)
I get the following error:
ValueError: None values not supported.
During handling of the above exception, another exception occurred:
ValueError Traceback (most recent call last)
ValueError: None values not supported.
During handling of the above exception, another exception occurred:
ValueError Traceback (most recent call last)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/op_def_library.py in _apply_op_helper(op_type_name, name, **keywords)
538 raise ValueError(
539 "Tried to convert '%s' to a tensor and failed. Error: %s" %
--> 540 (input_name, err))
541 prefix = ("Input '%s' of '%s' Op has type %s that does not match" %
542 (input_name, op_type_name, observed))
ValueError: Tried to convert 'shape' to a tensor and failed. Error: None values not supported. Kindly assist me on the same