Comments (3)
Actually, this error doesn't seem to be exclusive to raw datasets. A similar one seems to happen randomly for normal ones too. However, with a combination of certain config and tfrecords, I was able to get normal dataset to begin training, but never got a raw one to work.
It also may be worth noting I have a 6GB GPU. Pretty weak when compared to the recommended, but I was able to train fine on the normal stylegan2.
Edit: I think the error, when on normal datasets, is related to GPU memory, as they can often be fixed by changing gpu memory related parameters. However, that is ineffective against the error the occurs when using raw datasets.
from stylegan2-ada.
Error was due to mixed color formats in dataset
from stylegan2-ada.
What's the solution for it?
from stylegan2-ada.
Related Issues (20)
- Sorry, but I suspect your FID is fake HOT 8
- "W tensorflow/compiler/jit/mark_for_compilation_pass.cc:1412] (One-time warning): Not using XLA:CPU for cluster because envvar TF_XLA_FLAGS=--tf_xla_cpu_global_jit was not set. If you want XLA:CPU, either set that envvar, or use experimental_jit_scope to enable XLA:CPU. To confirm that XLA is active, pass --vmodule=xla_compilation_cache=1 (as a proper command-line flag, not via TF_XLA_FLAGS) or set the envvar XLA_FLAGS=--xla_hlo_profile. " & "tensorflow.python.framework.errors_impl.NotFoundError: /home/paperspace/stylegan2/dnnlib/tflib/_cudacache/fused_bias_act_afa4ff47e864043461655b92eafcdf5f.so: undefined symbol: _ZN10tensorflow12OpDefBuilder5InputESs" HOT 1
- Don't use pickle to share weights HOT 3
- (gen_img[:, 0, 0, 0] * 0 + loss_Gpl) ... but why? HOT 1
- NVCC error. Compilation of custom CUDA ops on Windows 10 for Tensorflow 2.x HOT 5
- Error: Unable to allocate 0 bytes for an array with shape HOT 2
- Continue training HOT 4
- nvcc fatal
- StyleGAN2 Pickle File not working
- transfer learning with custom dataset has dominant influence HOT 2
- ValueError: axes don't match array, images will work one run and not work the next
- NotImplementedError: Cannot convert a symbolic Tensor (Train_gpu0/Loss_R1/gradients/Train_gpu0/Augment_1/transform/ImageProjectiveTransformV2_grad/flat_transforms_to_matrices/strided_slice:0) to a numpy array.
- How to show real and fake loss in Colab?
- Model conversion to tf.keras.Model (external application)
- FFHQ download script broken HOT 5
- How to recover if training is interrupted
- Structure of a new training data set HOT 1
- Projection.py, Why the reconstruction of some images and not good wile for some images it is better
- Range for heuristic r_t and ADA issues
- I'm sorry, but I suspect your FID is fake
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 stylegan2-ada.