Comments (1)
Here is a part of the logs and I think it fluctuates:
"INFO:root:Epoch 0, Step 2000, loss: 0.0698222815990448, disc_loss: 0.003855810035020113
INFO:root:Epoch 0, Step 4000, loss: 0.10153232514858246, disc_loss: 0.0027087130583822727
INFO:root:Epoch 0, Step 6000, loss: 0.09570753574371338, disc_loss: 0.013898389413952827
INFO:root:Epoch 0, Step 8000, loss: 0.1152464747428894, disc_loss: 0.003877736860886216
INFO:root:Epoch time: 5668.203575849533
INFO:root:
pesq: 2.9439869927276034, csig: 4.347757358511038, cbak: 3.57811086328908, covl: 3.7087207256078827, ssnr: 9.00936124113099, stoi: 0.94614695583022
INFO:root:Epoch 1, Step 2000, loss: 0.07784414291381836, disc_loss: 0.020618950948119164
INFO:root:Epoch 1, Step 4000, loss: 0.061434850096702576, disc_loss: 0.043131016194820404
INFO:root:Epoch 1, Step 6000, loss: 0.06747680902481079, disc_loss: 0.001505840104073286
INFO:root:Epoch 1, Step 8000, loss: 0.04802854731678963, disc_loss: 0.014482944272458553
INFO:root:Epoch time: 5658.317040681839
INFO:root:Epoch 2, Step 2000, loss: 0.08109544962644577, disc_loss: 0.0069780051708221436
INFO:root:Epoch 2, Step 4000, loss: 0.07633058726787567, disc_loss: 0.006170968525111675
INFO:root:Epoch 2, Step 6000, loss: 0.08500031381845474, disc_loss: 0.0013521842192858458
INFO:root:Epoch 2, Step 8000, loss: 0.04127846658229828, disc_loss: 0.0018893849337473512
INFO:root:Epoch time: 5657.765841007233
INFO:root:Epoch 3, Step 2000, loss: 0.07090915739536285, disc_loss: 0.005887601524591446
INFO:root:Epoch 3, Step 4000, loss: 0.059316493570804596, disc_loss: 0.0012161008780822158
INFO:root:Epoch 3, Step 6000, loss: 0.10464320331811905, disc_loss: 0.0052590081468224525
INFO:root:Epoch 3, Step 8000, loss: 0.06500907987356186, disc_loss: 0.0010780195007100701
INFO:root:Epoch time: 5662.782829999924
INFO:root:
pesq: 3.1471768543462115, csig: 4.524800468872296, cbak: 3.714835821897046, covl: 3.9118528691825403, ssnr: 9.58391283335014, stoi: 0.9514108003033614
INFO:root:Epoch 4, Step 2000, loss: 0.03907656669616699, disc_loss: 0.008593665435910225
INFO:root:Epoch 4, Step 4000, loss: 0.0602584108710289, disc_loss: 0.003996850922703743
INFO:root:Epoch 4, Step 6000, loss: 0.12089455872774124, disc_loss: 0.0021806589793413877
INFO:root:Epoch 4, Step 8000, loss: 0.09586295485496521, disc_loss: 0.0031526663806289434
INFO:root:Epoch time: 5669.503582715988
INFO:root:Epoch 5, Step 2000, loss: 0.0668821632862091, disc_loss: 0.0061484831385314465
INFO:root:Epoch 5, Step 4000, loss: 0.04616473987698555, disc_loss: 0.0014118528924882412
INFO:root:Epoch 5, Step 6000, loss: 0.06401266157627106, disc_loss: 0.0012459662975743413
INFO:root:Epoch 5, Step 8000, loss: 0.05762811750173569, disc_loss: 0.0017574067460373044
INFO:root:Epoch time: 5669.170885562897
INFO:root:Epoch 6, Step 2000, loss: 0.09387986361980438, disc_loss: 0.002971608191728592
INFO:root:Epoch 6, Step 4000, loss: 0.10805267840623856, disc_loss: 0.00345245492644608
INFO:root:Epoch 6, Step 6000, loss: 0.1099756583571434, disc_loss: 0.00208111759275198
INFO:root:Epoch 6, Step 8000, loss: 0.052734144032001495, disc_loss: 0.002511049387976527
INFO:root:Epoch time: 5673.420320510864"
from cmgan.
Related Issues (20)
- RuntimeError: permute(sparse_coo): number of dimensions in the tensor input does not match the length of the desired ordering of dimensions i.e. input.dim() = 3 is not equal to len(dims) = 4 HOT 1
- RuntimeError HOT 3
- RuntimeError
- RuntimeError HOT 2
- About the decreasing of loss HOT 1
- Can not reproduce the results HOT 12
- Training can get stuck HOT 6
- Inferior results trained from scratch HOT 7
- RuntimeeError HOT 1
- Can not reproduce the results HOT 3
- Training GPU requirements
- File "pesq/cypesq.pyx", line 1, in init cypesq ImportError: numpy.core.multiarray failed to import (auto-generated because you didn't call 'numpy.import_array()' after cimporting numpy; use '<void>numpy._import_array' to disable if you are certain you don't need it)
- File "/anaconda3/envs/cmg/lib/python3.9/site-packages/torch/nn/parallel/distributed.py", line 578, in __init__ dist._verify_model_across_ranks(self.process_group, parameters) RuntimeError: NCCL error in: ../torch/csrc/distributed/c10d/ProcessGroupNCCL.cpp:957, invalid usage, NCCL version 21.0.3 ncclInvalidUsage: This usually reflects invalid usage of NCCL library (such as too many async ops, too many collectives at once, mixing streams in a group, etc). HOT 2
- How do you resample to 16000? HOT 1
- 时域Loss计算疑惑
- the training speed confusion
- My server has a 3090, but reports that I don't have a gpu HOT 1
- Test set requirements when training
- epochs
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 cmgan.