Comments (6)
There's just an issue in my logic (it's 10PM on a Friday night and I'm coding over an ssh connection on my phone <_<) this most recent commit should handle it.
from biggan-pytorch.
Actually one more mistake in my logic (I flipped the greater than the wrong way), but NOW this one should handle it.
from biggan-pytorch.
Ah, this would appear to be an issue with classes_per_sheet
being greater than the overall batch size. Should be fixed with this commit.
from biggan-pytorch.
I tried out that commit, though this leads to thisAttributeError: 'Tensor' object has no attribute 'sample_'
Here's more context:
11/250 ( 4.00%) (TE/ETA: 0:13 / 5:18) itr: 11, G_loss : +0.418, D_loss_real : +0.149, D_loss_fake : 12/250 ( 4.40%) (TE/ETA: 0:13 / 4:55) itr: 12, G_loss : -0.430, D_loss_real : +0.369, D_loss_fake : 13/250 ( 4.80%) (TE/ETA: 0:13 / 4:36) itr: 13, G_loss : -0.668, D_loss_real : +0.540, D_loss_fake : 14/250 ( 5.20%) (TE/ETA: 0:14 / 4:20) itr: 14, G_loss : -0.389, D_loss_real : +0.516, D_loss_fake : 15/250 ( 5.60%) (TE/ETA: 0:14 / 4:05) itr: 15, G_loss : -0.387, D_loss_real : +1.293, D_loss_fake : 16/250 ( 6.00%) (TE/ETA: 0:14 / 3:53) itr: 16, G_loss : +0.582, D_loss_real : +1.693, D_loss_fake : 17/250 ( 6.40%) (TE/ETA: 0:15 / 3:41) itr: 17, G_loss : +0.666, D_loss_real : +0.569, D_loss_fake : 18/250 ( 6.80%) (TE/ETA: 0:15 / 3:32) itr: 18, G_loss : +1.341, D_loss_real : +0.089, D_loss_fake : 19/250 ( 7.20%) (TE/ETA: 0:15 / 3:23) itr: 19, G_loss : +0.691, D_loss_real : +0.333, D_loss_fake : 20/250 ( 7.60%) (TE/ETA: 0:16 / 3:15) itr: 20, G_loss : +0.195, D_loss_real : +0.000, D_loss_fake : +1.365 Saving weights to weights/BigGAN_C100_seed2_Gch64_Dch64_bs50_nDs4_Glr2.0e-04_Dlr2.0e-04_Gnlrelu_Dnlrelu_GinitN02_DinitN02_ema...
Saving weights to weights/BigGAN_C100_seed2_Gch64_Dch64_bs50_nDs4_Glr2.0e-04_Dlr2.0e-04_Gnlrelu_Dnlrelu_GinitN02_DinitN02_ema/copy0...
Traceback (most recent call last):
File "train.py", line 227, in <module>
main()
File "train.py", line 224, in main
run(config)
File "train.py", line 206, in run
state_dict, config, experiment_name)
File "/workspace/BigGAN-PyTorch/train_fns.py", line 140, in save_and_sample
z_=z_)
File "/workspace/BigGAN-PyTorch/utils.py", line 892, in sample_sheet
z_.sample_()
AttributeError: 'Tensor' object has no attribute 'sample_'
Any ideas? Thank you
from biggan-pytorch.
I could comment out line 892 and not sample, but I would prefer to sample while training if possible.
from biggan-pytorch.
Not a problem. Thanks, let me try that commit.
from biggan-pytorch.
Related Issues (20)
- Training with 96x96 input HOT 1
- 我长期研究和改进GAN,如果对GAN或者深度学习感兴趣的可以联系我,联系方式,wechat: lovedaixiaobaby
- How can I improve the quality of generated images?
- AttributeError: 'Distribution' object has no attribute 'dist_type' HOT 2
- why the inception scores and FIDs are not comparable with the TF version?
- Out of memory HOT 3
- requirements.txt or library versions
- Training with ImageNet 64x64 HOT 1
- sampling out of memory HOT 1
- Correct attention layer implementation HOT 4
- y_ and y variables in training function
- Query about orthogonal regularization implementation
- collapsed samples
- Trouble training it from scratch
- BigGAN-deep pre-trained
- How to train BigGAN for image generation conditioned on text description? HOT 1
- set cross_replica as true got bad result HOT 1
- Output 80x688 images
- Problems when sampling
- The model was trained. How to generate the images?
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 biggan-pytorch.