yu20103983 / FOTS

FOTS tensorflow implementation, Include train and test, EAST+Rotate+CRNN. FOTS: Fast Oriented Text Spotting with a Unified Network
89 stars 35 forks source link

too long time to wait #21

Closed ggsonic closed 5 years ago

ggsonic commented 5 years ago

the code running enqueuer = GeneratorEnqueuer(generator(**kwargs), use_multiprocessing=True) print('Generator use 10 batches for buffering, this may take a while, you can tune this yourself.') enqueuer.start(max_queue_size=10, workers=num_workers)

8 cpu all go up, keep running for several hours, but gpu usage is 0, and seems not starting training.

ggsonic commented 5 years ago

my error, sorry.

6457tang commented 4 years ago

my error, sorry.

what is the error? I also meet the problem.