Comments (7)
Yes, updating pytorch solved the issue, thanks!
Have you successfully trained the model?
from phenaki-pytorch.
I had 1.10, i believe
Regarding training, how can videos of different shapes be inputted into the model? I try adding a video with frames of size (300, 620) and it didn't work because it expects the video to have dimension image_size
from phenaki-pytorch.
@gmegh oh that is recent, maybe i should downgrade and fix the root issue
supporting rectangular sized video is actually possible with this architecture! let me put it in my todos
are you a phd student at Stanford?
from phenaki-pytorch.
@gmegh Hi Guillem! Could you paste your full script? Also, you won't see anything but noise if you don't train the model on a big corpus of images and video, if you were expecting something different
from phenaki-pytorch.
Sure! Yeah, I understood that I would just get noise without training, but I was first trying to run it without training to see the output, and then train on that.
This is the full script (see below). I just copied the setup code you had at README. Thanks for the help!
import torch
import sys
import os
from phenaki_pytorch import Phenaki, CViViT, MaskGit, MaskGitTrainWrapper, TokenCritic, CriticTrainer, make_video
maskgit = MaskGit(
num_tokens = 5000,
max_seq_len = 1024,
dim = 512,
dim_context = 768,
depth = 6,
)
cvivit = CViViT(
dim = 512,
codebook_size = 5000,
image_size = 256,
patch_size = 32,
temporal_patch_size = 2,
spatial_depth = 4,
temporal_depth = 4,
dim_head = 64,
heads = 8
)
phenaki = Phenaki(
cvivit = cvivit,
maskgit = maskgit
).cuda()
videos = torch.randn(3, 3, 17, 256, 256).cuda() # (batch, channels, frames, height, width)
texts = [
'a whale breaching from afar',
'young girl blowing out candles on her birthday cake',
'fireworks with blue and green sparkles'
]
loss = phenaki(videos, texts)
loss.backward()
# do the above for many steps, then ...
video = phenaki.sample(text = 'a squirrel examines an acorn', num_frames = 17, cond_scale = 5.) # (1, 3, 17, 256, 256)
from phenaki-pytorch.
@gmegh oh strange, it runs for me, what version of pytorch are you on?
from phenaki-pytorch.
@gmegh oh great! which version were you on before?
no not yet, but should be in a state ready for training soon
from phenaki-pytorch.
Related Issues (20)
- Save video? HOT 4
- Different video sizes HOT 1
- Running out of CUDA/GPU spaces HOT 17
- Release pretrained models? HOT 6
- In phenaki to output video_codebook_ids... HOT 1
- how to run cvivit trainer or phenaki trainer HOT 8
- There is error in ema HOT 1
- model.buffer is EMPTY list in EMA get_buffers_iter function HOT 4
- I have a theoretical question about maskgit cross attention HOT 2
- ImportError: T5Tokenizer requires the SentencePiece library but it was not found in your environment. HOT 4
- What is out of index? HOT 1
- Unconditional Training returns errors HOT 5
- Einops Error. Shape mismatch HOT 2
- Compatibility issue with A100-80G with version 0.0.67 HOT 3
- discriminator loss goes to infinity HOT 12
- Problem With Multi-GPU Training HOT 2
- Where can find '/path/to/trained/cvivit.pt' HOT 1
- Successfully trained the CViViT! Working on the second step HOT 5
- Training the Phenaki - RuntimeError: CUDA error: device-side assert triggered HOT 2
- cannot reproduce HOT 7
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 phenaki-pytorch.