You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hey absolutely love the functionalities of this repo!! Thx so much!
However, I'm getting issues when running this on my local RTX 2080 Ti machine..
All the training ops run fine, except for the G_reg_op
The weird thing is that I just tested with the code from the official StyleGAN2 repo, and there everything seems to work perfectly (including G_reg_op)...
To summarize, the core of the error seems to originate in the custom cuda functions for upsampling:
I have tested that nvcc test_nvcc.cu -o test_nvcc -run runs correctly
Running Cuda 10.0, TF 1.14.0 and Python 3.6
When I switch off lazy regularization, all runs fine again
Running a config-f model on 1024x1024 res with (8, 8, res_log2 = 7) setting (is that the appropriate way of doing 1024x1024, or would you recommend (4,4, res_log2 = 8) ?
Here's the full traceback:
``dnnlib: Running training.training_loop.training_loop() on localhost...
Streaming data using training.dataset.TFRecordDataset...
####################################################
TFREC dir: datasets/fractal_tf_rec
['fractal_tf_rec-r07.tfrecords']
####################################################
Dataset shape = [3, 1024, 1024]
Dynamic range = [0, 255]
Label size = 0
Constructing networks...
Setting up TensorFlow plugin "fused_bias_act.cu": Preprocessing... Loading... Done.
Setting up TensorFlow plugin "upfirdn_2d.cu": Preprocessing... Loading... Done.
Ok, turns out this error is actually caused by setting sched.minibatch_gpu_base = 1 in run_training.py.
At first I was getting OOM errors, so I lowered the gpu_base, but if you set it to 1 you suddenly get this weird and uninformative error..
Hey absolutely love the functionalities of this repo!! Thx so much!
However, I'm getting issues when running this on my local RTX 2080 Ti machine..
All the training ops run fine, except for the G_reg_op
The weird thing is that I just tested with the code from the official StyleGAN2 repo, and there everything seems to work perfectly (including G_reg_op)...
To summarize, the core of the error seems to originate in the custom cuda functions for upsampling:
Here's the full traceback:
The text was updated successfully, but these errors were encountered: