【自己幫影片換主角】FakeApp 教學

第一步已經Fail左

cmd果步ffmpeg -i sceneA.mp4 -vf fps=30 "out%d.png"
直接出紅字sceneA.mp4: No such file or directory

ffmpeg sceneA 要同一folder

我都幾肯定一齊放左係users/user name

你多左個.mp4

其實玩左一次就唔想玩，第一時間太耐，十幾秒要用成幾個鐘，未計搵素材片，
加上個sw仲係唔穩定，玩一次夠

train係train個model 你train完一次用其他人樣都唔使再train
google "deep learning"啦
如果唔係都唔會咁爆啦單野

咩叫其他人樣都唔洗再train
train A + B
之後 同model
轉train 另一pair C+D 都?

即係你有b(av)同model
就可以自由換a(明星/你女神)嘅相

我估係咁

RuntimeError: module compiled against API version 0xc but this version of numpy is 0xb
0%| | 0/472 [00:00<?, ?it/s]
Traceback (most recent call last):
File "align_faces.py", line 145, in <module>
File "align_faces.py", line 136, in main
File "align_faces.py", line 116, in iter_face_alignments
File "site-packages\imread\imread.py", line 72, in imread
RuntimeError: Not a PNG file
[10644] Failed to execute script align_faces


明明data_A file都extract到
B就唔得

Traceback (most recent call last):
File "site-packages\PyInstaller\loader\pyiboot01_http://bootstrap.py", line 172, in _
_init__
File "ctypes\__init__.py", line 351, in __init__
OSError: [WinError 126] 找不到指定的模組。

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "site-packages\tensorflow\python\platform\self_http://check.py", line 75, in pre
load_check
File "site-packages\PyInstaller\loader\pyiboot01_http://bootstrap.py", line 174, in _
_init__
__main__.PyInstallerImportError: Failed to load dynlib/dll 'cudart64_80.dll'. Mo
st probably this dynlib/dll was not found when the application was frozen.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "http://train.py", line 37, in <module>
File "d:\anaconda\envs\merging\lib\site-packages\PyInstaller\loader\pyimod03_i
http://mporters.py", line 631, in exec_module
File "http://model.py", line 8, in <module>
File "d:\anaconda\envs\merging\lib\site-packages\PyInstaller\loader\pyimod03_i
http://mporters.py", line 631, in exec_module
File "site-packages\tensorflow\__init__.py", line 24, in <module>
File "d:\anaconda\envs\merging\lib\site-packages\PyInstaller\loader\pyimod03_i
http://mporters.py", line 631, in exec_module
File "site-packages\tensorflow\python\__init__.py", line 49, in <module>
File "d:\anaconda\envs\merging\lib\site-packages\PyInstaller\loader\pyimod03_i
http://mporters.py", line 631, in exec_module
File "site-packages\tensorflow\python\pywrap_http://tensorflow.py", line 30, in <modu
le>
File "site-packages\tensorflow\python\platform\self_http://check.py", line 82, in pre
load_check
ImportError: Could not find 'cudart64_80.dll'. TensorFlow requires that this DLL
be installed in a directory that is named in your %PATH% environment variable.
Download and install CUDA 8.0 from this URL: https://developer.nvidia.com/cuda-t
oolkit
[9476] Failed to execute script train

C:\Users\Hong\Desktop\FakeApp>


咩解究

1. 睇番CUDA個環境變數set左未 要係path放2個位置既話要係第一個地址之後加；再打第二個
2. Fakeapp個file可能要放番係C driver

重裝左cuda就解決左了，thx bro
依家問題係train嗰陣話我圖size唔啱
明明已經係256x256

呢個除左path錯之外真係諗唔到

屌原來真係c個大細階

我960啊 由凌晨3點到朝早起身就LOAD好哂

好難估

要自己del左佢

我果啲結衣bb 都有好多日清公仔面，要自己del

你地train到零點幾先停？

姐係你係訓練一個ai 你第一次train佢乜都唔識就緊係耐 但你玩多D佢就會越黎越快

唔明,巴打點解決

想問下如果我train 完一次再加相入去train多次會唔會有用?

ResourceExhaustedError (see above for traceback): OOM when allocating tensor with shape[3,3,1024,2048]
[[Node: training/Adam/Variable_12/Assign = Assign[T=DT_FLOAT, _class=["loc:@training/Adam/Variable_12"], use_locking=true, validate_shape=true, _device="/job:localhost/replica:0/task:0/device:GPU:0"](training/Adam/Variable_12, training/Adam/Const_14)]]

[376] Failed to execute script train

咩事

我覺得有用，宜家試緊
本身train咗8個鐘去到0.01幾
但好似唔夠圖
我宜家停咗再加啲新圖佢都喺0.01 ，0.02左右開始

嘥時間

[image2 @ 0000015e0f80e200] Could not open file : out1.png
av_interleaved_write_frame(): I/O error
唔知乜事step1嗰陣ffmpeg突然間彈呢個error
去到最後一步就permission denied
有冇巴打知點解

Traceback (most recent call last):
File "site-packages\PyInstaller\loader\pyiboot01_http://bootstrap.py", line 172, in _
_init__
File "ctypes\__init__.py", line 351, in __init__
OSError: [WinError 126] 找不到指定的模組。

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "site-packages\tensorflow\python\platform\self_http://check.py", line 75, in pre
load_check
File "site-packages\PyInstaller\loader\pyiboot01_http://bootstrap.py", line 174, in _
_init__
__main__.PyInstallerImportError: Failed to load dynlib/dll 'cudart64_80.dll'. Mo
st probably this dynlib/dll was not found when the application was frozen.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "http://train.py", line 37, in <module>
File "d:\anaconda\envs\merging\lib\site-packages\PyInstaller\loader\pyimod03_i
http://mporters.py", line 631, in exec_module
File "http://model.py", line 8, in <module>
File "d:\anaconda\envs\merging\lib\site-packages\PyInstaller\loader\pyimod03_i
http://mporters.py", line 631, in exec_module
File "site-packages\tensorflow\__init__.py", line 24, in <module>
File "d:\anaconda\envs\merging\lib\site-packages\PyInstaller\loader\pyimod03_i
http://mporters.py", line 631, in exec_module
File "site-packages\tensorflow\python\__init__.py", line 49, in <module>
File "d:\anaconda\envs\merging\lib\site-packages\PyInstaller\loader\pyimod03_i
http://mporters.py", line 631, in exec_module
File "site-packages\tensorflow\python\pywrap_http://tensorflow.py", line 30, in <modu
le>
File "site-packages\tensorflow\python\platform\self_http://check.py", line 82, in pre
load_check
ImportError: Could not find 'cudart64_80.dll'. TensorFlow requires that this DLL
be installed in a directory that is named in your %PATH% environment variable.
Download and install CUDA 8.0 from this URL: https://developer.nvidia.com/cuda-t
oolkit
[9476] Failed to execute script train

C:\Users\Hong\Desktop\FakeApp>


咩解究

1. 睇番CUDA個環境變數set左未 要係path放2個位置既話要係第一個地址之後加；再打第二個
2. Fakeapp個file可能要放番係C driver

重裝左cuda就解決左了，thx bro
依家問題係train嗰陣話我圖size唔啱
明明已經係256x256

呢個除左path錯之外真係諗唔到

屌原來真係c個大細階

唔明,巴打點解決

fakeapp 入path嗰三行
將代表c drive嘅C改做c

train 完禁Q係咪會自動save?

我一直用大階都冇事

想問data a同b圖片嘅數量係咪一定要一樣？