Question:
I’m trying to run the tensorflow backend and connect it to label studio and i get this error when training the model
server | ValueError: Attempting to slice scalar input. for '{{node strided_slice}} = StridedSlice[Index=DT_INT32, T=DT_FLOAT, begin_mask=0, ellipsis_mask=0, end_mask=0, new_axis_mask=0, shrink_axis_mask=1](args_0, strided_slice/stack, strided_slice/stack_1, strided_slice/stack_2)' with input shapes: [], [1], [1], [1] and with computed input tensors: input[3] = <1>.
Answer:
The error you’re encountering with the TensorFlow backend appears to be related to a slicing operation on a scalar input, which is not valid. This could be due to an issue with the input data being passed to the model during training. It’s important to ensure that the input data shapes and types match the expected format of the model.