Hi,
Is there any way to enter a different data set with much fewer labels?
for example, shapes and not objects like: plane, sphere, cylinder?
I tried doing this but I get an error that the tensor shape that is expected is 3 but it is receiving a tensor with 40 -->
"Traceback (most recent call last):
File "src/inference.py", line 39, in
model.load_weights(SAVED_MODEL)
File "C:\Python38\lib\site-packages\keras\utils\traceback_utils.py", line 67, in error_handler
raise e.with_traceback(filtered_tb) from None
File "C:\Python38\lib\site-packages\tensorflow\python\training\saving\saveable_object_util.py", line 133, in restore
raise ValueError(
ValueError: Received incompatible tensor with shape (40,) when attempting to restore variable with shape (3,) and name layer_with_weights-9/dense/bias/.ATTRIBUTES/VARIABLE_VALUE."
Hi, Is there any way to enter a different data set with much fewer labels? for example, shapes and not objects like: plane, sphere, cylinder? I tried doing this but I get an error that the tensor shape that is expected is 3 but it is receiving a tensor with 40 -->
"Traceback (most recent call last): File "src/inference.py", line 39, in
model.load_weights(SAVED_MODEL)
File "C:\Python38\lib\site-packages\keras\utils\traceback_utils.py", line 67, in error_handler
raise e.with_traceback(filtered_tb) from None
File "C:\Python38\lib\site-packages\tensorflow\python\training\saving\saveable_object_util.py", line 133, in restore
raise ValueError(
ValueError: Received incompatible tensor with shape (40,) when attempting to restore variable with shape (3,) and name layer_with_weights-9/dense/bias/.ATTRIBUTES/VARIABLE_VALUE."
Thanks a lot