how to projector no squar images?

[dayu1979]

After successfully training StyleGAN 2 on a dataset of (1024, 768), I tried using the network for projecting real images into latent space. Unfortunately I'm getting an error as shown below. Traceback (most recent call last):
File "run_projector.py", line 146, in
main()
File "run_projector.py", line 141, in main
dnnlib.submit_run(sc, func_name_map[subcmd], **kwargs)
File "/home/dayu/D/src2000/stylegan2_skyfly/dnnlib/submission/submit.py", line 343, in submit_run
return farm.submit(submit_config, host_run_dir)
File "/home/dayu/D/src2000/stylegan2_skyfly/dnnlib/submission/internal/local.py", line 22, in submit
return run_wrapper(submit_config)
File "/home/dayu/D/src2000/stylegan2_skyfly/dnnlib/submission/submit.py", line 280, in run_wrapper
run_func_obj(**submit_config.run_func_kwargs)
File "/home/dayu/D/src2000/stylegan2_skyfly/run_projector.py", line 59, in project_real_images
proj.set_network(Gs)
File "/home/dayu/D/src2000/stylegan2_skyfly/projector.py", line 103, in set_network
proc_images_expr = tf.reduce_mean(tf.reshape(proc_images_expr, [-1, sh[1], sh[2] // factor, factor, sh[2] // factor, factor]), axis=[3,5])
File "/home/dayu/anaconda3/lib/python3.7/site-packages/tensorflow/python/ops/gen_array_ops.py", line 7715, in reshape
"Reshape", tensor=tensor, shape=shape, name=name)
File "/home/dayu/anaconda3/lib/python3.7/site-packages/tensorflow/python/framework/op_def_library.py", line 788, in _apply_op_helper
op_def=op_def)
File "/home/dayu/anaconda3/lib/python3.7/site-packages/tensorflow/python/util/deprecation.py", line 507, in new_func
return func(*args, **kwargs)
File "/home/dayu/anaconda3/lib/python3.7/site-packages/tensorflow/python/framework/ops.py", line 3616, in create_op
op_def=op_def)
File "/home/dayu/anaconda3/lib/python3.7/site-packages/tensorflow/python/framework/ops.py", line 2027, in init
control_input_ops)
File "/home/dayu/anaconda3/lib/python3.7/site-packages/tensorflow/python/framework/ops.py", line 1867, in _create_c_op
raise ValueError(str(e))
ValueError: Dimension size must be evenly divisible by 3145728 but is 2359296 for 'Reshape' (op: 'Reshape') with input shapes: [1,3,1024,768], [6] and with input tensors computed as partial shapes: input[1] = [?,3,256,4,256,4].

[Anas-Khayata]

@skyflynil @dayu1979
do you have any solution for projection to latent space for non-square images?
I am also having the same error

Thanks