Skip to content
This repository has been archived by the owner on Nov 9, 2023. It is now read-only.

Can't parse "center" error immediately upon starting training #5723

Open
dave-mitchell opened this issue Sep 4, 2023 · 0 comments
Open

Can't parse "center" error immediately upon starting training #5723

dave-mitchell opened this issue Sep 4, 2023 · 0 comments

Comments

@dave-mitchell
Copy link

Expected behavior

Describe, in some detail, what you are trying to do and what the output is that you expect from the program.
I expect the model to begin training and building previews and models using my data_src/ and data_dst/ image data in my workspace.

Actual behavior

Describe, in some detail, what the program does instead. Be sure to include any error message or screenshots.
After running extract frames, detect faces, sort, enhance, and then Xseg, I'm getting the following error when I start the training.
I'm using a Colab notebook, fwiw. I edited my warp.py file as instructed by /gaurang1123 in issue 5403 but that didn't fix the issue.
Traceback (most recent call last): File "/usr/lib/python3.10/multiprocessing/process.py", line 314, in _bootstrap self.run() File "/usr/lib/python3.10/multiprocessing/process.py", line 108, in run self._target(*self._args, **self._kwargs) File "/content/DeepFaceLab/core/joblib/SubprocessGenerator.py", line 54, in process_func gen_data = next (self.generator_func) File "/content/DeepFaceLab/samplelib/SampleGeneratorFace.py", line 136, in batch_func raise Exception ("Exception occured in sample %s. Error: %s" % (sample.filename, traceback.format_exc() ) ) Exception: Exception occured in sample 00028.jpg. Error: Traceback (most recent call last): File "/content/DeepFaceLab/samplelib/SampleGeneratorFace.py", line 134, in batch_func x, = SampleProcessor.process ([sample], self.sample_process_options, self.output_sample_types, self.debug, ct_sample=ct_sample) File "/content/DeepFaceLab/samplelib/SampleProcessor.py", line 106, in process warp_params = imagelib.gen_warp_params(resolution, File "/content/DeepFaceLab/core/imagelib/warp.py", line 137, in gen_warp_params random_transform_mat = cv2.getRotationMatrix2D((w // 2, w // 2), rotation, scale) TypeError: Can't parse 'center'. Sequence item with index 0 has a wrong type

Steps to reproduce

Describe, in some detail, the steps you tried that resulted in the behavior described above.
The code to reproduce the issue is in the colab notebook for the project. Specifically the cell that's triggering the error is:

`#@title Training
Model = "SAEHD" #@param ["SAEHD", "AMP", "Quick96", "XSeg"]
Backup_every_hour = True #@param {type:"boolean"}
Silent_Start = True #@param {type:"boolean"}

%cd "/content"

#Mount Google Drive as folder
from google.colab import drive
drive.mount('/content/drive')

import psutil, os, time

p = psutil.Process(os.getpid())
uptime = time.time() - p.create_time()

if (Backup_every_hour):
if not os.path.exists('workspace.zip'):
print("Creating workspace archive ...")
!zip -0 -r -q workspace.zip workspace
print("Archive created!")
else:
print("Archive exist!")

if (Backup_every_hour):
print("Time to end session: "+str(round((43200-uptime)/3600))+" hours")
backup_time = str(3600)
backup_cmd = " --execute-program -"+backup_time+" "import os; os.system('zip -0 -r -q workspace.zip workspace/model'); os.system('cp /content/workspace.zip /content/drive/My\ Drive/'); print('Backed up!') ""
elif (round(39600-uptime) > 0):
print("Time to backup: "+str(round((39600-uptime)/3600))+" hours")
backup_time = str(round(39600-uptime))
backup_cmd = " --execute-program "+backup_time+" "import os; os.system('zip -0 -r -q workspace.zip workspace'); os.system('cp /content/workspace.zip /content/drive/My\ Drive/'); print('Backed up!') ""
else:
print("Session expires in less than an hour.")
backup_cmd = ""

cmd = "DeepFaceLab/main.py train --training-data-src-dir workspace/data_src/aligned --training-data-dst-dir workspace/data_dst/aligned --pretraining-data-dir pretrain --model-dir workspace/model --model "+Model

if Model == "Quick96":
cmd+= " --pretrained-model-dir pretrain_Q96"

if Silent_Start:
cmd+= " --silent-start"

if (backup_cmd != ""):
train_cmd = (cmd+backup_cmd)
else:
train_cmd = (cmd)

!python $train_cmd`

Other relevant information

  • Command lined used (if not specified in steps to reproduce): main.py ...
  • Operating system and version: Linux V100 GPU (via colab)
  • Python version: 3.5, 3.6.4, ... (if you are not using prebuilt windows binary)
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant