python random distribution from dimension

I have a 4D array, and I am trying to select from this array all of the first three dimensions and then a random distribution of the fourth dimension

samples = np.unique( np.random.randint(subset_start, subset_end, size=50) )    
layer_tensor = model.layer_tensors[model_layer][:, :, :, samples]

Which gives me:

ValueError: Shapes must be equal rank, but are 0 and 1
    **From merging shape 2 with other shapes. for 'strided_slice/stack_1' (op: 'Pack') with input shapes: [], [], [], [44].**