Got an error
billhhh opened this issue · 3 comments
Thank you so much for sharing your training code!! but I encountered an weired error, after running for 1 or 2 epoch, it occurs
current learning rate: 0.0010000000474974513
Traceback (most recent call last):
File "train.py", line 232, in
main()
File "train.py", line 215, in main
class_weight=class_weights,
File "/workspace/huwang/tools/anaconda3/lib/python3.6/site-packages/keras/legacy/interfaces.py", line 91, in wrapper
return func(*args, **kwargs)
File "/workspace/huwang/tools/anaconda3/lib/python3.6/site-packages/keras/engine/training.py", line 2213, in fit_generator
callbacks.on_epoch_end(epoch, epoch_logs)
File "/workspace/huwang/tools/anaconda3/lib/python3.6/site-packages/keras/callbacks.py", line 76, in on_epoch_end
callback.on_epoch_end(epoch, logs)
File "/home/mnt/StorageArray2_DGX1/huwang/dataset/CXR14/CheXNet-Keras-master-20170124/callback.py", line 76, in on_epoch_end
x, y = load_generator_data(self.generator, self.steps, len(self.class_names))
File "/home/mnt/StorageArray2_DGX1/huwang/dataset/CXR14/CheXNet-Keras-master-20170124/callback.py", line 22, in load_generator_data
batch_x, batch_y = next(generator)
ValueError: generator already executing
I am not that familiared with Keras. May I know how to solve it? Thx again
Try setting use_multiprocessing=True in fit_generator(). Let me know if that doesn't work for you.
It's working, thx, Bruce!!
GTK!