iankuoli / dfnet_tf2 Goto Github PK

i am facing same problem of Emaziz

the code is working but i am not getting expected results. when talking about test. py the output remains the same as with the mask applied on.

do i need to change the resolution in model. py and since i am using 256*256 image sample.

Also, the subplot that shows up is a bit messy.

@iankuoli please recheck the code files

NotFoundError: /root/Dataset/celeba/train_imgs_tiny; No such file or directory [Op:MatchingFiles]
while running task.py
how to change the directory path

Hi,
Can you please elaborate as to how we can convert the same to pytorch model.
also, the 'test' code throws below error when passed the model and other inputs

File "C:\Users\AZIZIAN\DFNet_TF2\trainer\test.py", line 242, in
tester.inpaint(args.output, args.img, args.mask, merge_result=args.merge)
File "C:\Users\AZIZIAN\DFNet_TF2\trainer\test.py", line 200, in inpaint
self.process_batch(batch, output)
File "C:\Users\AZIZIAN\DFNet_TF2\trainer\test.py", line 151, in process_batch
result, alpha, raw = self.model(imgs_miss, masks)
File "C:\Users\AZIZIAN\AppData\Roaming\Python\Python36\site-packages\tensorflow_core\python\keras\engine\base_layer.py", line 842, in call
outputs = self.call(cast_inputs, *args, **kwargs)
File "C:\Users\AZIZIAN\DFNet_TF2\trainer\model_legacy.py", line 219, in call
out = tf.concat([masked_img, mask], axis=-1)
File "C:\Users\AZIZIAN\AppData\Roaming\Python\Python36\site-packages\tensorflow_core\python\util\dispatch.py", line 180, in wrapper
return target(*args, **kwargs)
File "C:\Users\AZIZIAN\AppData\Roaming\Python\Python36\site-packages\tensorflow_core\python\ops\array_ops.py", line 1598, in concat
return gen_array_ops.concat_v2(values=values, axis=axis, name=name)
File "C:\Users\AZIZIAN\AppData\Roaming\Python\Python36\site-packages\tensorflow_core\python\ops\gen_array_ops.py", line 1180, in concat_v2
_ops.raise_from_not_ok_status(e, name)
File "C:\Users\AZIZIAN\AppData\Roaming\Python\Python36\site-packages\tensorflow_core\python\framework\ops.py", line 6637, in raise_from_not_ok_status
six.raise_from(core._status_to_exception(e.code, message), None)
File "", line 3, in raise_from
tensorflow.python.framework.errors_impl.InvalidArgumentError: ConcatOp : Dimensions of inputs should match: shape[0] = [4,3,32,32] vs. shape[1] = [4,1,32,32] [Op:ConcatV2] name: concat