def main():
print("\n", "/" * 120, "\n")
print(d.now())
print("\nOUTPUTS DIRECTORY:\n{}\n".format(activity_dir))
print("\nTRN H5:\n{}\n".format(trn_h5))
trn_ip = ip.for_callids(
trn_h5,
callids=trn_callids,
data_context=dctx,
add_channel_at_end=add_channel_dim,
label_subcontext=lctx,
label_from_subcontext_fn=lctx_fn,
steps_per_chunk=steps_per_chunk,
classkeyfn=np.argmax, # for categorical labels
class_subsample_to_ratios=trn_class_subsampling,
shuffle_seed=trn_shuffle_seed,
npasses=trn_passes, )
print(
"{}: max-totlen: {:,}; nchunks: {:,}; steps_per_pass: {:,}; npasses: {:,}".
format("TRN", trn_ip.totlen, trn_ip.nchunks, trn_ip.steps_per_pass,
trn_ip.npasses))
print("data shape: {}; label shape: {}".format(trn_ip.inputdatashape,
trn_ip.inputlabelshape))
print("\nVAL H5:\n{}\n".format(val_h5))
val_ip = ip.for_callids(
val_h5,
callids=val_callids,
data_context=dctx,
add_channel_at_end=add_channel_dim,
label_subcontext=lctx,
label_from_subcontext_fn=lctx_fn,
steps_per_chunk=steps_per_chunk,
classkeyfn=np.argmax, # for categorical labels
class_subsample_to_ratios=val_class_subsampling,
shuffle_seed=None, # never shuffled
npasses=1, )
print(
"{}: max-totlen: {:,}; nchunks: {:,}; steps_per_pass: {:,}; npasses: {:,}".
format("VAL", val_ip.totlen, val_ip.nchunks, val_ip.steps_per_pass,
val_ip.npasses))
print("data shape: {}; label shape: {}".format(val_ip.inputdatashape,
val_ip.inputlabelshape))
print("\nTST H5:\n{}\n".format(tst_h5))
tst_ip = ip.for_callids(
tst_h5,
callids=tst_callids,
data_context=dctx,
add_channel_at_end=add_channel_dim,
label_subcontext=lctx,
label_from_subcontext_fn=lctx_fn,
steps_per_chunk=steps_per_chunk,
classkeyfn=np.argmax, # for categorical labels
class_subsample_to_ratios=tst_class_subsampling,
shuffle_seed=None, # never shuffled
npasses=1, )
print(
"{}: max-totlen: {:,}; nchunks: {:,}; steps_per_pass: {:,}; npasses: {:,}".
format("TST", tst_ip.totlen, tst_ip.nchunks, tst_ip.steps_per_pass,
tst_ip.npasses))
print("data shape: {}; label shape: {}".format(tst_ip.inputdatashape,
tst_ip.inputlabelshape))
trn_gen = trn_ip.flow(
indefinitely=True,
only_labels=False,
with_chunking=False, )
nepochs = epochs_per_pass * trn_passes
steps_per_epoch = (trn_passes * trn_ip.steps_per_pass) // nepochs
val_gen = val_ip.flow(
indefinitely=True,
only_labels=False,
with_chunking=False, )
validation_steps = val_ip.steps_per_pass
callbacks = ku.create_callbacks(
val_ip,
activity_dir,
epochs_per_pass,
verbose=verbose == 1,
pickle_safe=pickle_safe,
max_q_size=max_q_size)
input_shape = trn_ip.inputdatashape
model = get_model(input_shape)
print("\n", "/" * 120, "\n")
print("MODEL SUMMARY")
model.summary()
print("\n", "/" * 120, "\n")
print("TRAINING BEGINS\n")
model.fit_generator(
trn_gen,
steps_per_epoch=steps_per_epoch,
epochs=nepochs,
validation_data=val_gen,
validation_steps=validation_steps,
callbacks=callbacks,
verbose=verbose,
pickle_safe=pickle_safe,
max_q_size=max_q_size,
initial_epoch=initial_epoch, )
print("\nTRAINING ENDED")
print(d.now())
print("\n", "/" * 120, "\n")
print("PREDICTING ON TEST")
ku.predict_on_inputs_provider(
model,
tst_ip,
activity_dir, )
print("\nDONE")
print(d.now())
def main():
print("\n", "/" * 120, "\n")
print(d.now())
print(
"\n\nCHUNKWISE", {
"no-n": "NON-NORMALIZED",
"m-n": "MEAN-NORMALIZED",
"mv-n": "MEAN-VARIANCE-NORMALIZED",
}[norm], {
"keepzero": "WITH-SILENCE",
"skipzero": "WITHOUT-SILENCE",
"skipzero-20one": "WITHOUT-SILENCE-SUBSAMPLED-SINGLE-SPEECH",
}[sub], "\n\n")
print("\nOUTPUTS DIRECTORY:\n{}\n".format(activity_dir))
# Create input providers and shout a bunch of things ######################
print("\nTRN H5:\n{}\n".format(trn_h5))
trn_ip = ip.for_callids(
trn_h5,
callids=trn_callids,
data_context=data_context,
add_channel_at_end=add_channel_dim,
label_subcontext=label_subcontext,
label_from_subcontext_fn=label_subcontext_fn,
steps_per_chunk=steps_per_chunk,
classkeyfn=np.argmax, # for categorical labels
class_subsample_to_ratios=trn_class_subsampling,
shuffle_seed=trn_shuffle_seed,
npasses=trn_passes,
mean_it=mean_it,
std_it=std_it,
)
print(
"{}: max-totlen: {:,}; nchunks: {:,}; steps_per_pass: {:,}; npasses: {:,}"
.format("TRN", trn_ip.totlen, trn_ip.nchunks, trn_ip.steps_per_pass,
trn_ip.npasses))
print("data shape: {}; label shape: {}".format(trn_ip.inputdatashape,
trn_ip.inputlabelshape))
print("\nVAL H5:\n{}\n".format(val_h5))
val_ip = ip.for_callids(
val_h5,
callids=val_callids,
data_context=data_context,
add_channel_at_end=add_channel_dim,
label_subcontext=label_subcontext,
label_from_subcontext_fn=label_subcontext_fn,
steps_per_chunk=steps_per_chunk,
classkeyfn=np.argmax, # for categorical labels
class_subsample_to_ratios=val_class_subsampling,
shuffle_seed=None, # never shuffled
npasses=1,
mean_it=mean_it,
std_it=std_it,
)
print(
"{}: max-totlen: {:,}; nchunks: {:,}; steps_per_pass: {:,}; npasses: {:,}"
.format("VAL", val_ip.totlen, val_ip.nchunks, val_ip.steps_per_pass,
val_ip.npasses))
print("data shape: {}; label shape: {}".format(val_ip.inputdatashape,
val_ip.inputlabelshape))
print("\nTST H5:\n{}\n".format(tst_h5))
tst_ip = ip.for_callids(
tst_h5,
callids=tst_callids,
data_context=data_context,
add_channel_at_end=add_channel_dim,
label_subcontext=label_subcontext,
label_from_subcontext_fn=label_subcontext_fn,
steps_per_chunk=steps_per_chunk,
classkeyfn=np.argmax, # for categorical labels
class_subsample_to_ratios=tst_class_subsampling,
shuffle_seed=None, # never shuffled
npasses=1,
mean_it=mean_it,
std_it=std_it,
)
print(
"{}: max-totlen: {:,}; nchunks: {:,}; steps_per_pass: {:,}; npasses: {:,}"
.format("TST", tst_ip.totlen, tst_ip.nchunks, tst_ip.steps_per_pass,
tst_ip.npasses))
print("data shape: {}; label shape: {}".format(tst_ip.inputdatashape,
tst_ip.inputlabelshape))
init, tran = read_normalized_viterbi_priors()
print("GOT VITERBI PRIORS")
# Setup stuff for training with keras #####################################
trn_gen = trn_ip.flow(
indefinitely=True,
only_labels=False,
with_chunking=False,
)
nepochs = epochs_per_pass * trn_passes
steps_per_epoch = (trn_passes * trn_ip.steps_per_pass
) // nepochs if trn_passes != 0 else 0
val_gen = val_ip.flow(
indefinitely=True,
only_labels=False,
with_chunking=False,
)
validation_steps = val_ip.steps_per_pass
callbacks = ku.create_callbacks(val_ip,
activity_dir,
epochs_per_pass,
verbose=verbose == 1,
pickle_safe=pickle_safe,
max_q_size=max_q_size)
input_shape = trn_ip.inputdatashape
model = get_model(input_shape)
print("\n", "/" * 120, "\n")
print("MODEL SUMMARY")
model.summary()
if steps_per_epoch != 0:
print("\n", "/" * 120, "\n")
print("TRAINING BEGINS\n")
model.fit_generator(
trn_gen,
steps_per_epoch=steps_per_epoch,
epochs=nepochs,
validation_data=val_gen,
validation_steps=validation_steps,
callbacks=callbacks,
verbose=verbose,
pickle_safe=pickle_safe,
max_q_size=max_q_size,
initial_epoch=initial_epoch,
)
print("\nTRAINING ENDED")
print(d.now())
print("\n", "/" * 120, "\n")
print("PREDICTING ON TEST")
export_to = os.path.join(activity_dir, "confs.test.h5")
predict_on_inputs_provider(model, tst_ip, export_to, init, tran)
print("\nDONE")
print(d.now())