Open OlgaGolovneva opened 5 years ago
Evaluating likelihood is straightforward, with, e.g., texar.losses.sequence_sparse_softmax_cross_entropy
. Here is an example of using the loss function:
https://github.com/asyml/texar/blob/master/examples/language_model_ptb/lm_ptb.py#L103-L106
Thanks a lot! Could you please help me also to figure out how I can change k, g, and d parameters (epochs and number of updates for discr training) mentioned in the original SeqGAN paper https://arxiv.org/pdf/1609.05473.pdf ?
Discriminator training is by the function _d_run_epoch
. You may customize it for more control.
The while-loop:
while True:
try:
# Training op here
except: tf.errors.OutOfRangeError:
break
is one-epoch training.
Thank you! How can I control the number of mini-batch gradient steps that discriminator runs with the same generator input? In the while-loop, it first updates negative examples from generator, and than updates discriminator once with combination of positive and negative samples.
You may make infer_sample_ids
here as a TF placeholder, and feed the same generator sample when optimizing the discriminator for multiple steps.
Thank you!
Is it possible to add Likelihood-based Metrics on generated data for SeqGan evaluation? They are described in original paper and paper accompanying implementation you refer to (https://arxiv.org/pdf/1802.01886.pdf)