Comments (3)
This is just an attempt we made. Here we still follow the Diffusion-LM approach, that is, x_output = x_start. That is, the corresponding predict_x_start=False in config.yaml.
There is indeed some confusion here with predict_xstart, but you don’t need to worry about predict_x_start. This is code that is convenient for debugging.
from prophetnet.
Please give the specific code location
from prophetnet.
Please give the specific code location
In the GaussianDiffusion's method "training_losses_s2s" one can notice that in the 1622th LoC (gaussian_diffusion.py) predict_x_start
is introduced (and this is the only one occurrence of that hyperparameter in the whole codebase of the AR-Diffusion):
if self.config.predict_x_start:
x_output = model_out_x_start
else:
x_output = x_start
The predict_xstart
is referenced plenty of times in the codebase and its behaviour is, in fact, the same as setting the model_mean_type to ModelMeanType.START_X - that is, AR-Diffusion outputs
# Usually our model outputs epsilon, but we re-derive it
# in case we used x_start or x_prev prediction.
from prophetnet.
Related Issues (20)
- Can use_fp16 be used?
- Why is the GENIE result in AR-diffusion very different from the original paper? Also, you come from a team. HOT 1
- Character level
- Can't Find Pretrained Checkpoint of Prophetnet: HOT 1
- Unable to load the GENIE model HOT 1
- The datasets have no dev set? HOT 1
- Options Employed for Training or Inference on the CNN/DM Dataset HOT 1
- It seems that the core code of CRITIC, particularly the part involving Google API search, is not implemented HOT 4
- Missing key documents for AR-Diffusion HOT 1
- where is "mbr_select.py" in AR-Diffusion HOT 1
- Unable to run Genie_Finetune.py HOT 1
- “load_fairseq” not found in "AR-Diffusion/data_utils" HOT 3
- Question for GENIE Finetuning, how to specify epochs for training/finetuning? HOT 1
- “load_fairseq” not found in "AR-Diffusion/data_utils" HOT 1
- AR-Diffusion data.name and exp.name HOT 2
- Request the execution code of llama2
- AR-diffusion: where the code for algorithm 1 is located? HOT 4
- (AR-Diffusion) RuntimeError: Error(s) in loading state_dict for CrossAttention_Diffusion_LM HOT 3
- what is the need for `num_samples` parameter in inference? 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 prophetnet.