Comments (2)
Hi,
Yes, tT_loss
does not pass the transformer layer, but there are still learnable params, i.e. the params of word embedding (from x_start
). We can regard it as a kind of regularization, so in Eq.17 we move it to
from diffuseq.
I am still confused about issue #17. The content of this issue has been duplicated as follow:
There is a tT_loss term in the final loss: DiffuSeq/diffuseq/gaussian_diffusion.py Lines 629 to 630 in 901f860
out_mean, _, _ = self.q_mean_variance(x_start, th.LongTensor([self.num_timesteps - 1]).to(x_start.device)) tT_loss = mean_flat(out_mean ** 2)
What is this? I cannot find it in the paper. And accroding to the code, the out_mean looks like the mean value of as from the diffusion forward procedure, and out_mean ** 2 should then be . Also, there seems no learnable params in the compute graph of tT_loss? I wonder what is this term for, what is the meaning, and where it comes from?
As for the comment from @yjc4 in #17, I think that term doesn't explain these issues, because obviously it has been dropped from step 1 to step 2 in equation (17) from the paper. Please provide me some hints. Thanks.
just by the way, it's issue #16
from diffuseq.
Related Issues (20)
- Problem about Running Time on Dialogue dataset HOT 1
- Some questions about different losses HOT 2
- On the calculation of Xt partial loss in Zt HOT 6
- Questions about "decoder_nll" HOT 3
- About Transformer Model HOT 1
- About loss in training_losses_seq2seq() when time step t=0 HOT 5
- facing an error while trying to execute pip install -r requirements.txt in terminal HOT 13
- Error when decoding HOT 1
- Only one gpu
- About the usage of `batch` in dataset (form of `batch`, `cond`) HOT 2
- Working with larger datasets HOT 2
- Dataset(2) in "text_datasets.py" HOT 1
- the Multi-GPU training acutally duplicates data in each GPU ? HOT 19
- Where decode "src" and "trg" ? HOT 1
- Nothing generated from decode HOT 2
- NCCL error
- License HOT 1
- Question About top-p sampling HOT 1
- q<n> metrics HOT 1
- NLL for q0-q2 is 0 but for q3 is >2 HOT 5
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 diffuseq.