-
Notifications
You must be signed in to change notification settings - Fork 2.1k
Description
Hi I am getting error when I use any of additional parameters available for the model, HR or with_scratch as True.
Any idea what is wrong ?
URL for model playground - https://replicate.com/microsoft/bringing-old-photos-back-to-life
Logs:
/src
Running Stage 1: Overall restoration
detection.py:25: DeprecationWarning: BICUBIC is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.BICUBIC instead.
def data_transforms(img, full_size, method=Image.BICUBIC):
initializing the dataloader
model weights loaded
directory of testing image: /src/input/cog_temp
processing tmp84o2t6f6A_Mikron 9x12 PR CZB T2 ZP .jpg
test.py:18: DeprecationWarning: BILINEAR is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.BILINEAR instead.
def data_transforms(img, method=Image.BILINEAR, scale=False):
You are using NL + Res
Now you are processing tmp84o2t6f6A_Mikron 9x12 PR CZB T2 ZP .png
Skip tmp84o2t6f6A_Mikron 9x12 PR CZB T2 ZP .png due to an error:
CUDA out of memory. Tried to allocate 717.81 GiB (GPU 0; 14.57 GiB total capacity; 4.60 GiB already allocated; 78.75 MiB free; 13.31 GiB reserved in total by PyTorch)
Finish Stage 1 ...
Running Stage 2: Face Detection
Finish Stage 2 ...
Running Stage 3: Face Enhancement
The main GPU is
0
dataset [FaceTestDataset] of size 0 was created
The size of the latent vector size is [16,16]
Network [SPADEGenerator] was created. Total number of parameters: 92.1 million. To see the architecture, do print(network).
hi :)
Finish Stage 3 ...
Running Stage 4: Blending
Finish Stage 4 ...
All the processing is done. Please check the results.
Traceback (most recent call last):
File "/root/.pyenv/versions/3.8.14/lib/python3.8/site-packages/cog/server/worker.py", line 352, in _predict
result = predict(**payload)
File "predict.py", line 177, in predict
final_output = os.listdir(os.path.join(self.output_folder, "final_output"))[0]
IndexError: list index out of range