Cannot do "Face_detect_crop" function #477
Assignees
CalvinBackup (Calvin Backup)
Clear assignees
CalvinBackup (Calvin Backup)
No Assignees
Notifications
Due Date
No due date set.
Dependencies
No dependencies set.
Reference: CalvinBackup/neuralchen-SimSwap#477
Reference in New Issue
Block a user
The --no-check-certificate file "antelope.zip"
https://sh23tw.dm.files.1drv.com/y4mmGiIkNVigkSwOKDcV3nwMJulRGhbtHdkheehR5TArc52UjudUYNXAEvKCii2O5LAmzGCGK6IfleocxuDeoKxDZkNzDRSt4ZUlEt8GlSOpCXAFEkBwaZimtWGDRbpIGpb_pz9Nq5jATBQpezBS6G_UtspWTkgrXHHxhviV2nWy8APPx134zOZrUIbkSF6xnsqzs3uZ_SEX_m9Rey0ykpx9w" -O antelope.zip
is unavailable.
I get errors: "FileNotFoundError Traceback (most recent call last) and "FileNotFoundError: [Errno 2] No such file or directory: './insightface_func/models'"
Is there a workaround? I need your help. Please.
You need to follow the https://github.com/neuralchen/SimSwap/blob/main/docs/guidance/preparation.md to download face detection and alignment models, but the download link doesn't work now.
@luoxyhappy can confirm link seems to be down at the moment.
Any idea how to source necessary files? Can anyone provide alternative download link?
@neuralchen @R3PO97 @luoxyhappy @bfirsh @TransAmMan In below code , there is link and this link is not available ? how i download ???
The --no-check-certificate file "antelope.zip"
https://sh23tw.dm.files.1drv.com/y4mmGiIkNVigkSwOKDcV3nwMJulRGhbtHdkheehR5TArc52UjudUYNXAEvKCii2O5LAmzGCGK6IfleocxuDeoKxDZkNzDRSt4ZUlEt8GlSOpCXAFEkBwaZimtWGDRbpIGpb_pz9Nq5jATBQpezBS6G_UtspWTkgrXHHxhviV2nWy8APPx134zOZrUIbkSF6xnsqzs3uZ_SEX_m9Rey0ykpx9w" -O antelope.zip
is unavailable.
#474 solved the problem. https://drive.google.com/file/d/1goH5lO8BAhTpRhpBeXqWEcGkxiiLlgx9/view @Maryam483 @TransAmMan @R3PO97
Can confirm link above works. Thanks!
The link in #474 appears to work. However, when you try to unzip the file "!unzip ./antelope.zip -d ./insightface_func/models/", it fails with error:
"Archive: ./antelope.zip
End-of-central-directory signature not found. Either this file is not
a zipfile, or it constitutes one disk of a multi-part archive. In the
latter case the central directory and zipfile comment will be found on
the last disk(s) of this archive.
unzip: cannot find zipfile directory in one of ./antelope.zip or
./antelope.zip.zip, and cannot find ./antelope.zip.ZIP, period."
I probably have to point the "unzip" command at a different directory. I am working on the issue. If anyone has an answer please let me know.
@neuralchen @R3PO97 @luoxyhappy @bfirsh
@neuralchen @R3PO97 @luoxyhappy @bfirsh yes the above .zip file works , thanks alot, but when i run this code as per steps mention in colab file, then the resulting generated video has blurr faces like an image below i have attached ??? why???
https://colab.research.google.com/github/neuralchen/SimSwap/blob/main/SimSwap%20colab.ipynb#scrollTo=wwJOwR9LNKRz
when i run:
!python test_one_image.py --name people --Arc_path arcface_model/arcface_checkpoint.tar --pic_a_path crop_224/6.jpg --pic_b_path crop_224/ds.jpg --output_path output/
it generates warnings also:
-------------- End ----------------
/content/SimSwap/models/base_model.py:70: FutureWarning: You are using
torch.loadwithweights_only=False(the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value forweights_onlywill be flipped toTrue. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user viatorch.serialization.add_safe_globals. We recommend you start settingweights_only=Truefor any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.pretrained_dict = torch.load(save_path)
Pretrained network G has fewer layers; The following are not initialized:
['down0', 'first_layer', 'last_layer', 'up0']
and wrong image
Hi: @Maryam483
I still cant get the zip file link to work for me. As for your problem with the distorted images. Try this change in the last cell.
opt.use_mask = True ## new feature up-to-date
opt.Arc_path = './arcface_model/arcface_checkpoint.tar'
opt.isTrain = False
opt.crop_size = 224
crop_size = opt.crop_size
torch.nn.Module.dump_patches = True
model = create_model(opt)
model.eval()
if crop_size == 512:
opt.which_epoch = 550000
opt.name = '512'
mode = 'ffhq'
else:
mode = 'None'
app = Face_detect_crop(name='antelope', root='./insightface_func/models')
app.prepare(ctx_id= 0, det_thresh=0.6, det_size=(640,640),mode=mode)
with torch.no_grad():
pic_a = opt.pic_a_path
HI: @luoxyhappy
Did you just replace the "url" like this:
!wget --no-check-certificate "https://drive.google.com/file/d/1goH5lO8BAhTpRhpBeXqWEcGkxiiLlgx9/view" -O antelope.zip
!unzip ./antelope.zip -d ./insightface_func/models/
or did you make other changes?
@neuralchen @R3PO97 @luoxyhappy @bfirsh @Maryam483
Yes, it should be correct.