vickyfox / region-wise-inpainting Goto Github PK

View Code? Open in Web Editor NEW

53.0 53.0 17.0 3.33 MB

Region-wise GAN, image inpainting

License: MIT License

Python 100.00%

region-wise-inpainting's People

Contributors

Stargazers

Watchers

Forkers

ssttfit paddletutorial-v2 lifeixianshen mayureshpitale eridgd coco2dslesson yjingyu appearancefnp must4in3 zcemycl xiankgx avani17101 hhheeexxxuuu jhonatas-17 rongisdragon icewang12138 cin-inpaiting

region-wise-inpainting's Issues

The contiguous testing results

Hello, I used contiguous masks for training on the Paris Street View datasets. However, the test results have visible artifacts such as blurring .It seems that the adversarial network has no influence on predicted images. I used the fourth adversarial loss function in the code. Can you give me some suggestions?

cv2.resize() has wrong order for height/width args

Hi, thank you for sharing such an interesting model.

I noticed that the cv2.resize() calls in test.py have the wrong order for height/width resize args. OpenCV reverses the usual convention for whatever reason.

This line

Region-wise-Inpainting/test.py

Line 45 in 005fe51

test_mask = cv2.resize(cv2.imread(file_mask),(args.height,args.width))

should be:

test_mask = cv2.resize(cv2.imread(file_mask),(args.width, args.height))

and similarly for

Region-wise-Inpainting/test.py

Line 52 in 005fe51

test_image = cv2.resize(test_image, (args.height, args.width))

Dataset structure

How to set up the data set structure during training?

Pre-trained models

Hello, I have a question for your pre-trained models. Are these pre-trained models you have given the best result?

test pretrained model error

Good job.
I have a question. When I test the pretrained mode, there are some problems which were as follows.

2019-10-12 09:06:49.561403: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2019-10-12 09:06:49.818430: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1030] Found device 0 with properties: 
name: Tesla K80 major: 3 minor: 7 memoryClockRate(GHz): 0.8235
pciBusID: 0000:91:00.0
totalMemory: 11.92GiB freeMemory: 11.85GiB
2019-10-12 09:06:49.818465: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1120] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: Tesla K80, pci bus id: 0000:91:00.0, compute capability: 3.7)
WARNING:tensorflow:From /data/mm.bai/anaconda3/lib/python3.6/site-packages/tensorflow/python/util/tf_should_use.py:107: initialize_all_variables (from tensorflow.python.ops.variables) is deprecated and will be removed after 2017-03-02.
Instructions for updating:
Use `tf.global_variables_initializer` instead.
WARNING:tensorflow:From /data/mm.bai/anaconda3/lib/python3.6/site-packages/tensorflow/python/util/tf_should_use.py:107: initialize_local_variables (from tensorflow.python.ops.variables) is deprecated and will be removed after 2017-03-02.
Instructions for updating:
Use `tf.local_variables_initializer` instead.
2019-10-12 09:06:51.953352: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:51.954590: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:51.955549: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:51.956806: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:51.959782: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:51.959920: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:51.960713: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:51.962097: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:51.963103: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:51.964368: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:51.964930: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:51.965643: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:51.966036: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:51.967070: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:51.967984: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:51.968596: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:51.969829: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:51.970371: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:51.971469: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:51.972139: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:51.974451: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:51.974687: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:51.975544: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:51.976396: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:51.976957: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:51.977636: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:51.978238: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:51.981614: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:51.982434: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:51.984263: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:51.989938: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:51.992244: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:51.994950: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:51.995119: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:51.997206: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:52.003494: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:52.005046: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:52.006706: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:52.007458: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:52.008163: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:52.016922: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:52.019257: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:52.027359: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:52.029062: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:52.030711: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:52.031078: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:52.032489: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:52.033111: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:52.034523: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:52.036541: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:52.044015: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:52.044232: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:52.046119: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:52.048949: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:52.049121: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:52.049948: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:52.051498: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:52.052054: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:52.052489: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:52.056027: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:52.056330: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:52.056548: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:52.057025: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:52.057608: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:52.058218: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:52.058705: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:52.059205: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:52.064305: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:52.065916: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
2019-10-12 09:06:52.066059: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
Traceback (most recent call last):
  File "/data/mm.bai/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1323, in _do_call
    return fn(*args)
  File "/data/mm.bai/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1302, in _run_fn
    status, run_metadata)
  File "/data/mm.bai/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/errors_impl.py", line 473, in __exit__
    c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.NotFoundError: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
	 [[Node: save/RestoreV2_51 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2_51/tensor_names, save/RestoreV2_51/shape_and_slices)]]
	 [[Node: save/RestoreV2_40/_21 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device_incarnation=1, tensor_name="edge_164_save/RestoreV2_40", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:GPU:0"]()]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/data/mm.bai/inpainting/paper_model/region_wise_inpainting/Region-wise-Inpainting-master/test.py", line 43, in <module>
    saver_pre.restore(sess,args.model_path)
  File "/data/mm.bai/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1666, in restore
    {self.saver_def.filename_tensor_name: save_path})
  File "/data/mm.bai/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 889, in run
    run_metadata_ptr)
  File "/data/mm.bai/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1120, in _run
    feed_dict_tensor, options, run_metadata)
  File "/data/mm.bai/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1317, in _do_run
    options, run_metadata)
  File "/data/mm.bai/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1336, in _do_call
    raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.NotFoundError: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
	 [[Node: save/RestoreV2_51 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2_51/tensor_names, save/RestoreV2_51/shape_and_slices)]]
	 [[Node: save/RestoreV2_40/_21 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device_incarnation=1, tensor_name="edge_164_save/RestoreV2_40", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:GPU:0"]()]]

Caused by op 'save/RestoreV2_51', defined at:
  File "/data/mm.bai/inpainting/paper_model/region_wise_inpainting/Region-wise-Inpainting-master/test.py", line 40, in <module>
    saver_pre=tf.train.Saver()
  File "/data/mm.bai/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1218, in __init__
    self.build()
  File "/data/mm.bai/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1227, in build
    self._build(self._filename, build_save=True, build_restore=True)
  File "/data/mm.bai/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1263, in _build
    build_save=build_save, build_restore=build_restore)
  File "/data/mm.bai/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 751, in _build_internal
    restore_sequentially, reshape)
  File "/data/mm.bai/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 427, in _AddRestoreOps
    tensors = self.restore_op(filename_tensor, saveable, preferred_shard)
  File "/data/mm.bai/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 267, in restore_op
    [spec.tensor.dtype])[0])
  File "/data/mm.bai/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/gen_io_ops.py", line 1021, in restore_v2
    shape_and_slices=shape_and_slices, dtypes=dtypes, name=name)
  File "/data/mm.bai/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
    op_def=op_def)
  File "/data/mm.bai/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 2956, in create_op
    op_def=op_def)
  File "/data/mm.bai/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1470, in __init__
    self._traceback = self._graph._extract_stack()  # pylint: disable=protected-access

NotFoundError (see above for traceback): Unsuccessful TensorSliceReader constructor: Failed to find any matching files for models/
	 [[Node: save/RestoreV2_51 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2_51/tensor_names, save/RestoreV2_51/shape_and_slices)]]
	 [[Node: save/RestoreV2_40/_21 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device_incarnation=1, tensor_name="edge_164_save/RestoreV2_40", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:GPU:0"]()]]

I think the checkpoint model of tensorflow should include 4 files, which are checkpoint, .index, .meta and .data.
Please check it.
Thank you.

Which adversarial loss is used in the paper?

Hello! Thanks for your awesome work. I am new in image inpainting. There is a question confusing me. I found the adversarial loss is important for artifacts. But I did not find the type of it. In the code, it contains wgan loss, gan loss and hinge loss. Could you tell me which is uesd in the paper? Thanks very much!

Training hyper params for Places2

Hello, nice paper! We are willing to publish our paper (regarding inpainting) and need to compare our model with yours. We have different strategy for mask generation and therefore to make comparison fair, we need to retrain your model on our masks. Can you specify how many gpus, what hyperparams (argsparse args) do you used and what was the training process for Places2?

Is it also possible, that you share multigpu code ?

Results of EC on Celeba-HQ

@vickyFox Hello,good work! And i have a small question.
You mentioned in the paper you directly apply the released pretrained model of CA, EC, PIC, but to my knowledge, EC didn't supply pretrained model on CelebA-HQ, so where did you get the results of it?

Published

Thanks for your work. I noticed that your article is pre-published on arXiv and I was wondering if it was published in some official journal?

Removal of clamp from book?

Hello
I am going to remove clamp from book image.
Is it possible to use this repository for this?

Pre-Trained Model

I have been trying to use this code as a novice. Downloaded the places2 model from GDrive, But I end up getting this error

Tensor name "inpaint_net/com_13_fusion_1/bias" not found in checkpoint files places_model/places2.ckpt-6666.index. Could you please help

Training on custom dataset with custom mask

Hello @vickyFox @shihaobai
Great work on the paper and even the results look amazing!

Can you please guide me with step by step process on how we need to prepare a dataset for a custom image dataset with a custom mask (if possible)?

How the masks will look like in the sense that whether it will be a colour image on which white patches (the part that will be inpainted from the model) is drawn or it will be a completely black image on which white patches (the part that will be inpainted from the model) is drawn? (in short how to prepare mask and then how to supply it for model training)

I referred to your steps but couldn't completely follow them.
Thank you in advance!

Questions about training

@vickyFox ,Thank you for your work!I have trained the model in my dataset?But the loss is very big(10e5) as follow!Could you give me some advice?

Only works on low quality images

Hello, thanks for sharing your work, the results are impressive!
I've compared to other in-painting methods and this gives a very good result, the main issue is width should equal to height and small size 256*256 which is preventing from testing on real world images, can you add support for non square photos?

Meta file for pre-trained models

Hi, google drive links doesnt contains META file. Is there a possible way to get it?

Results

Hello, I have two questions about your results in the table2 and table3 of the paper. When you compare with other methods on the CelebA-HQ dataset, are all algorithms tested with 2000 images? What's more, I noticed that the mask has a range of values such as 0-10%. So did you take the intermediate value such as 5%, or take several values such as 1%, 5% and 10%, and then average the psnr results?

train on places2

did you adopt the whole places2 dataset to train the model? how many hours does it take for each stage on places? thx~

Failed precondition:models Pretrained model

Hi I have error:
models: Failed precondition:models; Is a directory: perhaps your file is in a different file format and you need to use a different restore operator?

places2.ckpt-6666.index
places2.ckpt-6666.data.00001-of-00002

stackoweflow says to rename the models to places2.ckpt-6666.data -but its doesn't work for me.

can u help me please?

Pretrained models

Thank you for your work! You have provided two pretrained models: Pretrained model and ijcai Pretrained model. What is the difference between them? I have trained the model with 28000 face dataset and using wgan-gp loss with ijcai Pretrained model when the value of stage is one . But the model does not converge as follows. What' more, I think the code of wgan_gp loss should be change a little. Another question is how many iterations do you used? Could you give me some advice?

Coding error

Hi, in test.py,

test_mask = cv2.resize(cv2.imread(file_mask),(args.height, args.width)) should be changed to
test_mask = cv2.resize(cv2.imread(file_mask),(args.width, args.height))

as well as for

test_image = cv2.resize(test_image, (args.width, args.height))

Testing results

Hello, I have a question about the result. In the testing phase, it was found that the repaired image would appear blurry when the damaged area is large, as shown in figures below. Can you give me some suggestions?

What's more, I calculate the average FID value is 16 when the mask area is between 20% and 30%, which is larger than that in the paper. Did you normalize it?

No satisfactory results on high-resolution image inpainting

Hi, I tried on an 1080X1920 image with a large area-filled mask. The results seems not ok to me:

Could you explain why it didn't work, or do you know any literature that can deal that very well?

Thanks.

Recommend Projects

React

A declarative, efficient, and flexible JavaScript library for building user interfaces.
Vue.js

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
TensorFlow

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
D3

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

javascript

JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
web

Some thing interesting about web. New door for the world.
server

A server is a program made to process requests and deliver data to clients.
Machine learning

Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.