def main(args):
logging.getLogger("tensorflow").setLevel(logging.ERROR)
setproctitle.setproctitle('quakenet')
tf.set_random_seed(1234)
#pos_path = os.path.join(cfg.DATASET,"positive")
pos_path = os.path.join(os.path.join(dataset_dir, "train"),
cfg.output_tfrecords_dir_positives)
if not os.path.exists(pos_path):
print("[train] \033[91m ERROR!!\033[0m Missing directory " + pos_path +
". Run step 2 first.")
sys.exit(0)
neg_path = os.path.join(os.path.join(dataset_dir, "train"),
cfg.output_tfrecords_dir_negatives)
if not os.path.exists(neg_path):
print("[train] \033[91m ERROR!!\033[0m Missing directory " + neg_path +
". Run step 3 first.")
sys.exit(0)
print("[train] path to positives = " + pos_path)
print("[train] path to negaties = " + neg_path)
# data pipeline for positive and negative examples
pos_pipeline = dp.DataPipeline(pos_path, cfg, True)
neg_pipeline = dp.DataPipeline(neg_path, cfg, True)
pos_samples = {
'data': pos_pipeline.samples,
'cluster_id': pos_pipeline.labels
}
neg_samples = {
'data': neg_pipeline.samples,
'cluster_id': neg_pipeline.labels
}
samples = {
"data":
tf.concat(0, [pos_samples["data"], neg_samples["data"]]),
"cluster_id":
tf.concat(0, [pos_samples["cluster_id"], neg_samples["cluster_id"]])
}
# model
model = models.get(cfg.model,
samples,
cfg,
checkpoint_dir,
is_training=True)
# train loop
model.train(cfg.learning_rate,
resume=cfg.resume,
profiling=cfg.profiling,
summary_step=10,
checkpoint_step=cfg.checkpoint_step,
max_checkpoint_step=cfg.max_checkpoint_step)
def main(args):
setproctitle.setproctitle('quakenet')
tf.set_random_seed(1234)
if args.n_clusters == None:
raise ValueError('Define the number of clusters with --n_clusters')
cfg = config.Config()
cfg.batch_size = args.batch_size
cfg.add = 1
cfg.n_clusters = args.n_clusters
cfg.n_clusters += 1
pos_path = os.path.join(args.dataset, "positive")
neg_path = os.path.join(args.dataset, "negative")
# data pipeline for positive and negative examples
pos_pipeline = dp.DataPipeline(pos_path, cfg, True)
neg_pipeline = dp.DataPipeline(neg_path, cfg, True)
pos_samples = {
'data': pos_pipeline.samples,
'cluster_id': pos_pipeline.labels
}
neg_samples = {
'data': neg_pipeline.samples,
'cluster_id': neg_pipeline.labels
}
samples = {
"data":
tf.concat(0, [pos_samples["data"], neg_samples["data"]]),
"cluster_id":
tf.concat(0, [pos_samples["cluster_id"], neg_samples["cluster_id"]])
}
# model
model = models.get(args.model,
samples,
cfg,
args.checkpoint_dir,
is_training=True)
# train loop
model.train(args.learning_rate,
resume=args.resume,
profiling=args.profiling,
summary_step=10)
def main(_):
cfg = config.Config()
cfg.batch_size = 1
cfg.n_epochs = 1
data_pipeline = dpp.DataPipeline(FLAGS.data_path,
config=cfg,
is_training=False)
samples = data_pipeline.samples
labels = data_pipeline.labels
start_time = data_pipeline.start_time
end_time = data_pipeline.end_time
with tf.Session() as sess:
coord = tf.train.Coordinator()
tf.initialize_local_variables().run()
threads = tf.train.start_queue_runners(coord=coord)
try:
for i in (range(FLAGS.windows)):
to_fetch = [samples, labels, start_time, end_time]
sample, label, starttime, endtime = sess.run(to_fetch)
# assert starttime < endtime
print('starttime {}, endtime {}'.format(
UTCDateTime(starttime), UTCDateTime(endtime)))
print("label", label[0])
sample = np.squeeze(sample, axis=(0, ))
target = np.squeeze(label, axis=(0, ))
except tf.errors.OutOfRangeError:
print 'Evaluation completed ({} epochs).'.format(cfg.n_epochs)
print "{} windows seen".format(i + 1)
coord.request_stop()
coord.join(threads)
def main(_):
cfg = config.Config()
cfg.batch_size = 1
# Make dirs
if not os.path.exists(FLAGS.output_path):
os.makedirs(FLAGS.output_path)
data_pipeline = dpp.DataPipeline(FLAGS.data_path,
config=cfg,
is_training=False)
samples = data_pipeline.samples
labels = data_pipeline.labels
with tf.Session() as sess:
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord)
print '+ Plotting {} windows'.format(FLAGS.windows)
for i in tqdm(range(FLAGS.windows)):
sample, label = sess.run([samples, labels])
sample = np.squeeze(sample, axis=(0, ))
target = np.squeeze(label, axis=(0, ))
plt.clf()
fig, ax = plt.subplots(3, 1)
for t in range(sample.shape[1]):
ax[t].plot(sample[:, t])
ax[t].set_xlabel('time (samples)')
ax[t].set_ylabel('amplitude')
ax[0].set_title('window {:04d}, cluster_id: {}'.format(i, target))
plt.savefig(
os.path.join(FLAGS.output_path, 'window_{:04d}.pdf'.format(i)))
plt.close()
coord.request_stop()
coord.join(threads)
def main(args):
setproctitle.setproctitle('quakenet_debug')
if not os.path.exists(args.output):
os.makedirs(args.output)
if args.n_clusters == None:
raise ValueError('Define the number of clusters with --n_clusters')
cfg = config.Config()
cfg.batch_size = 1
cfg.n_epochs = 1
cfg.add = 2
cfg.n_clusters = args.n_clusters
cfg.n_clusters +=1
# data pipeline
data_pipeline = dp.DataPipeline(args.dataset, cfg, False)
samples = {
'data': data_pipeline.samples,
'cluster_id': data_pipeline.labels
}
# model
model_name = args.model
model = models.get(model_name, samples,
cfg, args.checkpoint_dir, is_training=False)
with tf.Session() as sess:
coord = tf.train.Coordinator()
tf.initialize_local_variables().run()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
model.load(sess)
step = sess.run(model.global_step)
print 'Debugging at step {}'.format(step)
# summary_writer = tf.train.SummaryWriter(model.checkpoint_dir, None)
activations = tf.get_collection(tf.GraphKeys.ACTIVATIONS)
weights = tf.get_collection(tf.GraphKeys.WEIGHTS)
biases = tf.get_collection(tf.GraphKeys.BIASES)
toget = {}
toget['0_input'] = model.inputs['data']
for i, a in enumerate(activations):
name = a.name.replace('/', '_').replace(':', '_')
toget['{}_{}'.format(i+1, name)] = a
for it in range(10):
print 'running session'
fetched = sess.run(toget)
print fetched
print it
for f in fetched:
d = fetched[f]
d = np.squeeze(d, axis=0)
plt.figure()
if len(d.shape) == 2:
for i in range(d.shape[1]):
plt.plot(d[:, i])
# tot_mean = np.mean(np.mean(d,axis=1),axis=0)
# plt.plot(np.mean(d,axis=1) / tot_mean)
plt.savefig(os.path.join(args.output, '{}_{}.pdf'.format(it, f)))
plt.clf()
coord.request_stop()
coord.join(threads)