DefakeHop Unable to train the model

Hey, It is a nice work and really appreciated.

I am getting an error when i run python model.py. May i ask you what could be the problem? Thanks!

Screenshot from 2021-12-08 15-44-53

Dec 08 '21 08:12 wasim004

Please pull the newest version of the code! We have updated the code!

Dec 08 '21 22:12 hongshuochen

Thank you for the response, Where i can find that? Thanks!

Dec 09 '21 05:12 wasim004

I have fixed that issue, Now I am getting another issue. Can you please have a look at it? Thanks! Screenshot from 2021-12-10 15-56-36

Dec 10 '21 07:12 wasim004

Do you use your own videos? This should be the expected output if you use my data.

==============================left_eye============================== ===============DefakeHop Prediction=============== ===============MultiChannelWiseSaab Transformation=============== Hop1 Input shape: (2708, 32, 32, 3) Output shape: (2708, 15, 15, 13)

Dec 13 '21 08:12 hongshuochen

Hi, Thanks for your kind response. Your output looks like:

Screenshot from 2021-12-13 17-04-01

The final result was like:

Screenshot from 2021-12-13 17-08-34

Dec 13 '21 09:12 wasim004

I used CelebDF-V1 dataset. I preprocessed the dataset, and create .npz files as per the requirements of the model. But I got this error. Screenshot from 2021-12-10 15-56-36

Dec 13 '21 09:12 wasim004

Sorry for the late reply! Here is the data for Celeb-DF-v1! I follow the same code and get this data! And please update the model.py, I think there was a small error due to the change of the structure of this repo! https://drive.google.com/drive/folders/1nEBe5wGPmm2G1NsR46NK8msHiCUE9f8K?usp=sharing

Please let me know whether you can get the results or not! Thank you!

Dec 15 '21 21:12 hongshuochen

Thank you so much for your kind response!

Well, I already modified the mpdel.py, thanks. But I got the same error even on your data. Please have a look at it.

Thanks! Screenshot from 2021-12-16 12-56-24

Dec 16 '21 05:12 wasim004

Could you help me check this part of code in model.py? test_images should be a 4D numpy array!

    for region in model.regions:
        path = 'data/' + region + '.test.npz'
        data = np.load(path)
        test_labels = data['labels']
        test_images = data['images']
        test_names = data['names']
        model.predict_region(region, test_images, test_names)

Dec 16 '21 07:12 hongshuochen

Thank you for the response..!

Sure, you may have a look at it. Thanks! Screenshot from 2021-12-16 17-37-59

Dec 16 '21 09:12 wasim004

Line169 and 170 are wrong And please load the testing data by np.load since we made some changes for the structure of this repo

Dec 16 '21 12:12 hongshuochen

Thank You so much..!! Finally solved the issue.

But still have to run some other datasets and I am unable to do that due to less memory of the system. Anyway thank you for your time and help. Will contact you if faced any other issue.

Thanks!

Dec 21 '21 08:12 wasim004

Hey,I extract feature data(celeb-v2) with shape (761334,32,32,3), it will out of memory when i run model.py So how do you run the large dataset? Thanks!

Dec 25 '21 10:12 DeepDetector

Hey,I extract feature data(celeb-v2) with shape (761334,32,32,3), it will out of memory when i run model.py So how do you run the large dataset? Thanks!

Hey, I am having the same issue and I asked one of the author of the paper and she said I can divide the data in chunks and train the model. But I am trying to arrange the resources for me, as I believe that it will effect the performance of the model and our results wouldn't be comparable to this work or others due to different circumstances. Thanks!

Dec 25 '21 12:12 wasim004

Hi! Thank you for your questions! It is a really great question! I will update the code for this problem! The idea is that we subsample the dataset and we use subset to train the Saab transform. For prediction, the whole dataset is used by dividing the dataset to many chunks and predict each chunks one by one! For Saab transform, we could use a subset to get the kernels which is demonstrated that it will get similar kernel when the number of samples is large. For XGBoost, we still use all the samples to train! I will update the code as soon as possible!

Dec 25 '21 19:12 hongshuochen

Thank you for the response！ And looking forward to your update~

Dec 27 '21 01:12 DeepDetector

Solved! Please try the new saab.py!

Dec 30 '21 08:12 hongshuochen

Hi, I tried to run it but this time the issue seems different. Thanks!

Screenshot from 2021-12-30 17-02-59

Solved! Please try the new saab.py!

Dec 30 '21 09:12 wasim004

Did you update the saab.py? Could you show me the fit in saab.py?

Dec 30 '21 20:12 hongshuochen

Thank you!The new saab.py work. But this time the issue is xgboost,it still need much memory. $K1_D4{9 }~J8)U)~P($JN6Q$

Dec 31 '21 01:12 DeepDetector

[](https://github.com/hongshuochen/DefakeHop/blob/941efb6a3d11b59bf0c4d56c95f75612a9f4da4e/defakeHop.py#L155) Change gpu_hist to hist

Dec 31 '21 05:12 hongshuochen

[](

https://github.com/hongshuochen/DefakeHop/blob/941efb6a3d11b59bf0c4d56c95f75612a9f4da4e/defakeHop.py#L155

) Change gpu_hist to hist

Thank you for your response! But now I hava the same issue as @wasim004 I updata saab.py and only modify file path. It will be killed at right eye region with shape(134069,32,32,3)

Dec 31 '21 08:12 DeepDetector

https://github.com/hongshuochen/DefakeHop/blob/941efb6a3d11b59bf0c4d56c95f75612a9f4da4e/saab.py#L38

Could you check which line in fit you program get killed?

Dec 31 '21 08:12 hongshuochen

https://github.com/hongshuochen/DefakeHop/blob/941efb6a3d11b59bf0c4d56c95f75612a9f4da4e/saab.py#L38

Could you check which line in fit you program get killed?

Hi, I updated saab.py but still getting same error. Screenshot from 2022-01-01 16-43-05

Jan 01 '22 08:01 wasim004

Hey,i guess the issue is still about out of memory.I entered three shapes:

(100000,32,32,3): It work!
(134069,32,32,3): Killed.
(761334,32,32,3): MemoryError: Unable to allocate array with shape (761334,32,32,3). The error in saab.py at output = np.zeros((N, H, W, n_channels), dtype="float64")

Jan 04 '22 04:01 DeepDetector

Please change all "float64" to "float32" in saab.py! And change the batch size from 50000 to 10000! https://github.com/hongshuochen/DefakeHop/blob/941efb6a3d11b59bf0c4d56c95f75612a9f4da4e/saab.py#L111

Jan 04 '22 06:01 hongshuochen

Hi @hongshuochen,

I've finally managed to run and train the model and got the results. I trained the model both on the original and modified code of saab.py for CelebDF-v2 dataset. I got the results below:

Screenshot from 2022-01-05 15-43-38

In your original paper the results are different than what I've got for the CelebDF-v2 dataset. Do you've any idea what could be the possible reason?

Jan 05 '22 07:01 wasim004

Also I train the model on CelebDF-v1. I have got the following results:

My Data: Frame(0.7971), Video(0.8453) Yours Data: Frame(0.9138), Video(0.9363)

Jan 05 '22 08:01 wasim004

The reason for this is that you change from "float64" to "float32" If you run with "float32" you can get the results that I get!

Jan 05 '22 08:01 hongshuochen

The reason for this is that you change from "float64" to "float32" If you run with "float32" you can get the results that I get!

Hi, Thanks for the response. I did not changed anything. I run your code as it is, because I find out a server to run your code so I don't have to modify anything in the code. Thanks!

Jan 05 '22 09:01 wasim004