Comments (6)
Solved: used with torch.cuda.amp.autocast():
in kernel_utils, line 334, for the subsquent 3 lines. & then changed all pointers to cuda with "cpu", removed the .half()'s where they were as incompatible with cpu use.
from dfdc_deepfake_challenge.
@guyreading @selimsef torch.cuda.amp.autocast()
is not available in PYTORCH="1.4"
which the Docker image is built for.
Is there a workaround you would recommend?
from dfdc_deepfake_challenge.
@epiqueras There is no need to use amp
for inference on CPU. You can just change half -> float inputs and device to "cpu" as @guyreading did.
from dfdc_deepfake_challenge.
@selimsef yeah, I ended up figuring that out reading the docs.
Thanks for confirming!
This doesn't do too well on side shots, does it? I tested it, and it gave me ~0.3 for an obviously fake video.
from dfdc_deepfake_challenge.
@epiqueras Yes, multiple reasons for that:
- less training data for that view
- In the training set there were two actors per video with side shots, one of them was not fake. So it created a lot of noise in training.
- MTCNN might miss faces on side shots or bounding boxes won't be accurate
from dfdc_deepfake_challenge.
@selimsef interesting; thanks for the info.
I tested it on frontal webcam shots, and it works almost perfectly.
What are your thoughts on using MTCNN vs. using some sort of reversal/adaptation of the feedback loops the networks that generate deepfakes use? I assume that would only work for targeting specific algorithms and using approaches like yours can work against a broader range of techniques?
from dfdc_deepfake_challenge.
Related Issues (20)
- I encountered continuous target data is not supported with label binarization
- Timm library version problem HOT 2
- Could you explain what does the argument "fold" mean HOT 2
- Could you explain how to built "metadata.json" in utils.py? HOT 1
- could i download pretrained model about dfdc dataset? Now I get an error. HOT 1
- Unable to understand extraction of crops HOT 2
- metadata.json HOT 2
- ValueError: Found array with 0 sample(s) (shape=(0,)) while a minimum of 1 is required. HOT 1
- Issue with bitmap masks. HOT 1
- Resize the videos HOT 1
- Why RuntimeError: cuDNN error: CUDNN_STATUS_NOT_INITIALIZED? HOT 2
- generate_folds.py Line 106 KeyError HOT 1
- top accuracy is 65.18% ? HOT 4
- submission.csv all predictions are below 0.5 HOT 7
- Google Colab HOT 3
- training dataset?
- CUDNN_STATUS_NOT_INITIALIZED
- Does this detect face filters?
- I find there is something wrong with " remove_landmark " code HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from dfdc_deepfake_challenge.