Ungayifaka kanjani i-DeepFaceLab ku-Linux ukudala amavidiyo ajulile

Luis Lopez

Imizuzu ye-2

Iminyaka eminingana ku-intanethi kukhona okuthiwa amavidiyo ajulile, kodwa ezinyangeni ezedlule ukuthandwa kwayo kuye kwanda kakhulu ngenxa yamathuluzi ahlukahlukene nezinhlelo zokusebenza ezenza kube lula ukwakha.

I-Deepfake inqubo esetshenziselwa ukuguqula izithombe noma amavidiyo kusetshenziswa ubuhlakani bokuzenzela, ezimweni eziningi kusetshenziselwa ukuphakamisa ubuso obubodwa kobunye, ngaleyo ndlela kudalwe amavidiyo angamanga ngemiphumela emihle.

Ngaphambi kwalokho, ukudala amavidiyo ajulile bekuyikhono elithathe iminyaka ukufunda, kepha manje, ngokuthuthuka kobuchwepheshe, kulula kakhulu ukukwenza.

I-DeepFaceLab iyithuluzi elitholakalayo le-Linux nezinye izinhlelo ezikuvumela ukuthi udale amavidiyo ajulile ngendlela elula usebenzisa umugqa womyalo.

Kungabonakala ngathi ukusebenzisa i-DeepFaceLab kunzima kakhulu ukukusebenzisa, kepha akukho okude nokuphikisana nalokhu, ngokusebenzisa nje imibhalo embalwa ungaguqula ividiyo bese ungeza ubuso obusha ku-protagonist.

Ungayifaka kanjani i-DeepFaceLab ku-Linux

Ukufaka i-DeepFaceLab kuzofanela uqale ufake i-Anaconda3 usebenzisa i- ikhasi elisemthethweni bese-ke kuzofanela uyiqale ngemiyalo elandelayo:

thekelisa PATH = ~ / anaconda3 / bin: $ PATH conda init bash

Manje usungaqhubeka nokufakwa kwe-DeepFacebLab ngemigqa elandelayo yekhodi:

conda create -y -n deepfacelab python = 3.6.6 cudatoolkit = 9.0 cudnn = 7.3.1 conda activate deepfacelab git clone https://github.com/lbfs/DeepFaceLab_Linux.git cd DeepFaceLab_Linux python -m pip install -r requirements-cuda .txt

Uma une-Ubuntu 16.04 noma i-18.04 ungabheka ikhasi elisemthethweni lokwakha izindlela zokufaka i-DeepFaceLab kuzona zombili lezi zinhlelo.

Ukusebenzisa i-DeepFaceLab kungaba nzima kepha uma ufunda lesi sifundo esivuselelwa njalo uzokwazi ukudala amavidiyo wakho wokujula njengochwepheshe.

Uma unezinkinga ngokufakwa noma ukusetshenziswa kwe-DeepFaceLab, sizokujabulela ukukusiza kumazwana.


Shiya umbono wakho

Ikheli lakho le ngeke ishicilelwe. Ezidingekayo ibhalwe nge *

*

*

  1. Unomthwalo wemfanelo ngedatha: AB Internet Networks 2008 SL
  2. Inhloso yedatha: Lawula Ugaxekile, ukuphathwa kwamazwana.
  3. Ukusemthethweni: Imvume yakho
  4. Ukuxhumana kwemininingwane: Imininingwane ngeke idluliselwe kubantu besithathu ngaphandle kwesibopho esisemthethweni.
  5. Isitoreji sedatha: Idatabase ebanjwe yi-Occentus Networks (EU)
  6. Amalungelo: Nganoma yisiphi isikhathi ungakhawulela, uthole futhi ususe imininingwane yakho.

  1.   U-Rugher kusho
    kwenza iminyaka 5

    Ngingaqala kanjani uhlelo uma selufakiwe noma ngingaqinisekisa kanjani ukuthi luyasebenza?

    Phendula uRugher
  2.   UHUGO FERNANDO CARRERA TOASA kusho
    kwenza iminyaka 5

    Siyabonga ngokwabelana
    njengoba ngixazulula okulandelayo.
    IPHUTHA: Ayikwazanga ukuthola inguqulo eyanelisa imfuneko tensorflow-gpu == 1.12.0 (from -r requirements-cuda.txt (line 5)) (from versions: 1.13.0rc1, 1.13.0rc2, 1.13.1, 1.13.2 .1.14.0, 0rc1.14.0, 1rc1.14.0, 1.15.0, 0rc2.0.0, 0a2.0.0, 0b2.0.0, 1b2.0.0, 0rc2.0.0, 1rcXNUMX).
    IPHUTHA: Akukho kusatshalaliswa okufanayo kwe-tensorflow-gpu == 1.12.0 (from -r requirements-cuda.txt (line 5))
    Ngicela ungisize

    Phendula ku-HUGO FERNANDO CARRERA TOASA
  3.   Ricardo kusho
    kwenza iminyaka 4

    Sawubona,

    Kunginikeza iphutha elifanayo nelikaHUGO FERNANDO CARRERA TOASA

    IPHUTHA: Ayikwazanga ukuthola inguqulo eyanelisa imfuneko tensorflow-gpu == 1.12.0 (from -r requirements-cuda.txt (line 5)) (from versions: 1.13.0rc1, 1.13.0rc2, 1.13.1, 1.13.2 .1.14.0, 0rc1.14.0, 1rc1.14.0, 1.15.0, 0rc1.15.0, 1rc1.15.0, 2rc1.15.0, 3rc1.15.0, 2.0.0, 0a2.0.0, 0b2.0.0, 1b2.0.0, 0rc2.0.0. , 1rc2.0.0, 2rc2.0.0, XNUMX)
    IPHUTHA: Akukho kusatshalaliswa okufanayo kwe-tensorflow-gpu == 1.12.0 (from -r requirements-cuda.txt (line 5))

    Phendula uRicardo
  4.   UFrancisco Diaz Carsí kusho
    kwenza iminyaka 3

    Sawubona,
    Uthi "Ukusebenzisa i-DeepFaceLab kungaba nzima kepha uma usufunde lesi sifundo esihlala sisesikhathini uzokwazi ukudala amavidiyo wakho wokujula njengochwepheshe." kepha ikuphi isifundo sokusebenzisa?

    Ngiyabonga imikhonzo.

    Phendula uFrancisco Díaz Carsí
  5.   Guillermo kusho
    kwenza iminyaka 3

    Sawubona, sawubona, ngicela ukwazi uma othile engangisiza nge-deepface yamawindi 10. Inkinga ukuthi ngiyayilanda futhi ngilandele izinyathelo zesifundo sevidiyo, faka abashayeli bekhadi lemidwebo le-nvidia, i-cuda_9.0.176 _win10.exe, i-cuda_9.0.176.1_windows.exe patch, i-cudnn-9.0-windows10-x64-v7.6.5.32.zip umtapo wolwazi kanye nohlelo lwe-deepface. Ngenze zonke izinyathelo kepha lapho ngivula uhlelo ngithola lelo windi elincane elingenalutho elisho lokhu: Changelog:
    - Ama-squirrel autoupdates
    - Ukwengeza kabusha amasethi wedatha wesithombe
    - Iphutha lobuso obungaguquki
    - Izinketho zokuhlanganisa ezingezwe kabusha
    - Ithuthukiselwe ku-TF 1.5, CUDA 9
    Khumbula ukulanda nokufaka umtapo wezincwadi oyinhloko. Uma isilandiwe yafakwa njengemiyalo esithangamini, phinda ulayishe uhlelo lokusebenza futhi lo mlayezo uzokwenza
    zinyamalale.
    Lokho kusho ukuthi uhlelo aluvuleki kimi. Ngingaluthokozela kakhulu noma yiluphi usizo onganginika lona. Ngiyabonga kakhulu. UWilliam

    Phendula uGuillermo