def run_experiment(general_cfg, seed):
tf.set_random_seed(seed)
np.random.seed(seed)
ds = EnhancersData('/cs/grad/pazbu/paz/dev/projects/dnanet-v2/data')
x = tf.placeholder(tf.float32, shape=[None, 4, 1000])
y_ = tf.placeholder(tf.uint8, shape=[None, 2])
keep_prob = tf.placeholder(tf.float32)
y_conv = CNN(x, dropout_keep_prob=keep_prob)
cross_entropy = tf.nn.softmax_cross_entropy_with_logits(labels=y_,
logits=y_conv)
train_step = tf.train.AdamOptimizer(1e-2).minimize(cross_entropy)
y_pred_sig = tf.sigmoid(y_conv)
correct_prediction = tf.equal(tf.argmax(y_, 1), tf.argmax(y_pred_sig, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
num_runs = 2
num_epochs = general_cfg["num_epochs"]
mini_batch_size = general_cfg["batch_size"]
iters_per_epoch = int(ds.train.num_examples / mini_batch_size)
with tf.Session() as sess:
print('run, epoch, step, training accuracy, validation accuracy')
for run_idx in range(num_runs):
sess.run(tf.global_variables_initializer())
for epoch_idx in range(num_epochs):
for iter_idx in range(iters_per_epoch):
batch = ds.train.next_batch(mini_batch_size)
if iter_idx % 100 == 0:
# out = y_.eval(feed_dict={x: batch[0], y_: batch[1], keep_prob: 1.0})
# print(out)
train_accuracy = accuracy.eval(feed_dict={
x: batch[0],
y_: batch[1],
keep_prob: 1.0
})
valid_accuracy = accuracy.eval(
feed_dict={
x: ds.validation.seqs,
y_: ds.validation.labels,
keep_prob: 1.0
})
print('%d, %d, %d, %g, %g' %
(run_idx, epoch_idx, iter_idx, train_accuracy,
valid_accuracy))
train_step.run(feed_dict={
x: batch[0],
y_: batch[1],
keep_prob: 0.5
})
print('test accuracy %g' % accuracy.eval(feed_dict={
x: ds.test.seqs,
y_: ds.test.labels,
keep_prob: 1.0
}))
def run_experiment(general_cfg, seed):
tf.set_random_seed(seed)
np.random.seed(seed)
data_dir_path = '/cs/grad/pazbu/paz/dev/projects/dnanet-v2/data'
ds = EnhancersData(data_dir_path)
log_files(data_dir_path)
x = tf.placeholder(tf.float32, shape=[None, 4, 1000], name="x")
y_ = tf.placeholder(tf.uint8, shape=[None, 2], name="y_")
keep_prob = tf.placeholder(tf.float32, name="keep_prob")
y_conv = CNN(x, dropout_keep_prob=keep_prob)
cross_entropy = tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv)
# attach update ops used for the batch normalization
update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
with tf.control_dependencies(update_ops):
train_step = tf.train.AdamOptimizer().minimize(cross_entropy)
y_pred_sig = tf.sigmoid(y_conv, name="sigmoid_out")
correct_prediction = tf.equal(tf.argmax(y_, 1), tf.argmax(y_pred_sig, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
num_runs = general_cfg["num_runs"]
num_epochs = general_cfg["num_epochs"]
mini_batch_size = general_cfg["batch_size"]
for var in tf.trainable_variables():
tf.summary.histogram(var.name, var)
merged_summary_op = tf.summary.merge_all()
saver = tf.train.Saver()
best_val_acc = 0
with tf.Session() as sess:
for run_idx in range(num_runs):
sess.run(tf.global_variables_initializer())
summary_writer = tf.summary.FileWriter("/cs/grad/pazbu/paz/dev/projects/dnanet-v2/summaries", graph=sess.graph)
current_step = 0
while ds.train.epochs_completed < num_epochs:
current_step += 1
batch = ds.train.next_batch(mini_batch_size)
if current_step % 100 == 0:
train_accuracy = accuracy.eval(feed_dict={x: batch[0], y_: batch[1], keep_prob: 1.0})
val_corrects = []
for x_val_batch, y_val_batch in ds.validation.single_pass_batch_iter(1000):
val_corrects.extend(correct_prediction.eval(feed_dict={x: x_val_batch,
y_: y_val_batch,
keep_prob: 1.0}))
valid_accuracy = sum(val_corrects) / ds.validation.num_examples
if best_val_acc < valid_accuracy:
saver.save(sess, save_path='chk', global_step=current_step)
best_val_acc = valid_accuracy
print('run: %d, epoch: %d, iteration: %d, train accuracy: %g, validation accuracy: %g' %
(run_idx, ds.train.epochs_completed, current_step, train_accuracy, valid_accuracy))
summary_str, _ = sess.run([merged_summary_op, train_step], feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
summary_writer.add_summary(summary_str, current_step)
def run_experiment(general_cfg, seed):
tf.set_random_seed(seed)
np.random.seed(seed)
data_dir_path = '/cs/grad/pazbu/paz/dev/projects/dnanet-v2/data'
ds = EnhancersData(data_dir_path)
log_files(data_dir_path)
x = tf.placeholder(tf.float32, shape=[None, 4, 1000])
y_ = tf.placeholder(tf.uint8, shape=[None, 2])
keep_prob = tf.placeholder(tf.float32)
y_conv = CNN(x, dropout_keep_prob=keep_prob)
cross_entropy = tf.nn.softmax_cross_entropy_with_logits(labels=y_,
logits=y_conv)
train_step = tf.train.AdamOptimizer(1e-2).minimize(cross_entropy)
y_pred_sig = tf.sigmoid(y_conv)
correct_prediction = tf.equal(tf.argmax(y_, 1), tf.argmax(y_pred_sig, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
num_runs = 2
num_epochs = general_cfg["num_epochs"]
mini_batch_size = general_cfg["batch_size"]
iters_per_epoch = int(ds.train.num_examples / mini_batch_size)
sv = tf.train.Supervisor(
logdir="/cs/grad/pazbu/paz/dev/projects/dnanet-v2/chk")
with sv.managed_session() as sess:
for step in range(100000):
if sv.should_stop():
break
batch = ds.train.next_batch(mini_batch_size)
if step % 100 == 0:
# out = y_.eval(feed_dict={x: batch[0], y_: batch[1], keep_prob: 1.0})
# print(out)
train_accuracy = accuracy.eval(feed_dict={
x: batch[0],
y_: batch[1],
keep_prob: 1.0
})
valid_accuracy = accuracy.eval(
feed_dict={
x: ds.validation.seqs,
y_: ds.validation.labels,
keep_prob: 1.0
})
print(
'run: %d, epoch: %d, iteration: %d, train accuracy: %g, validation accuracy: %g'
% (0, 0, step, train_accuracy, valid_accuracy))
train_step.run(feed_dict={
x: batch[0],
y_: batch[1],
keep_prob: 0.5
})
def run_experiment(general_cfg, seed):
tf.set_random_seed(seed)
np.random.seed(seed)
data_dir_path = '/cs/grad/pazbu/paz/dev/projects/dnanet-v2/data'
ds = EnhancersData(data_dir_path)
log_files(data_dir_path)
x = tf.placeholder(tf.float32, shape=[None, 4, 1000])
y_ = tf.placeholder(tf.uint8, shape=[None, 2])
keep_prob = tf.placeholder(tf.float32)
y_conv = CNN(x, dropout_keep_prob=keep_prob)
cross_entropy = tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv)
train_step = tf.train.AdamOptimizer(1e-2).minimize(cross_entropy)
y_pred_sig = tf.sigmoid(y_conv)
correct_prediction = tf.equal(tf.argmax(y_, 1), tf.argmax(y_pred_sig, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
num_runs = 2
num_epochs = general_cfg["num_epochs"]
mini_batch_size = general_cfg["batch_size"]
iters_per_epoch = int(ds.train.num_examples / mini_batch_size)
for var in tf.trainable_variables():
tf.summary.histogram(var.name, var)
merged_summary_op = tf.summary.merge_all()
with tf.Session() as sess:
for run_idx in range(num_runs):
sess.run(tf.global_variables_initializer())
summary_writer = tf.summary.FileWriter("/cs/grad/pazbu/paz/dev/projects/dnanet-v2/summaries",
graph=sess.graph)
for epoch_idx in range(num_epochs):
for iter_idx in range(iters_per_epoch):
batch = ds.train.next_batch(mini_batch_size)
if iter_idx % 100 == 0:
train_accuracy = accuracy.eval(feed_dict={x: batch[0], y_: batch[1], keep_prob: 1.0})
valid_accuracy = accuracy.eval(feed_dict={x: ds.validation.seqs,
y_: ds.validation.labels,
keep_prob: 1.0})
print('run: %d, epoch: %d, iteration: %d, train accuracy: %g, validation accuracy: %g' %
(run_idx, epoch_idx, iter_idx, train_accuracy, valid_accuracy))
_, summary_str = sess.run([train_step, merged_summary_op], feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
# summary_str = sess.run(merged_summary_op, feed_dict={x: ds.validation.seqs,
# y_: ds.validation.labels,
# keep_prob: 1.0})
summary_writer.add_summary(summary_str, iters_per_epoch*epoch_idx + iter_idx)
print('test accuracy %g' % accuracy.eval(feed_dict={x: ds.test.seqs, y_: ds.test.labels, keep_prob: 1.0}))
def run_experiment(general_cfg, dropout_keep_prob, seed):
tf.set_random_seed(seed)
np.random.seed(seed)
ds = EnhancersData(data_dir)
log_files(data_dir)
x = tf.placeholder(tf.float32, shape=[None, 4, general_cfg["seq_length"]], name="x")
y_ = tf.placeholder(tf.float32, shape=[None, general_cfg["num_outs"]], name="y_")
keep_prob = tf.placeholder(tf.float32, name="keep_prob")
y_conv = CNN(x, dropout_keep_prob=keep_prob)
cross_entropy = tf.losses.sigmoid_cross_entropy(multi_class_labels=y_, logits=y_conv)
train_step = tf.train.AdamOptimizer().minimize(cross_entropy)
y_pred_sig = tf.sigmoid(y_conv, name="sigmoid_out")
correct_prediction = tf.equal(y_, tf.round(y_pred_sig))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
num_runs = general_cfg["num_runs"]
num_epochs = general_cfg["num_epochs"]
mini_batch_size = general_cfg["batch_size"]
for var in tf.trainable_variables():
tf.summary.histogram(var.name, var)
merged_summary_op = tf.summary.merge_all()
saver = tf.train.Saver()
best_val_acc = 0
ex_id = ex.current_run._id
class_weights = np.sum(ds.test.labels, axis=0) / np.sum(ds.test.labels)
with tf.Session() as sess:
for run_idx in range(num_runs):
chkp_dir = path.join(ex_log_dir, str(ex_id), "run" + str(run_idx))
ds.reset()
sess.run(tf.global_variables_initializer())
summary_writer = tf.summary.FileWriter("/cs/grad/pazbu/paz/dev/projects/dnanet-roadmap/summaries", graph=sess.graph)
current_step = 0
while ds.train.epochs_completed < num_epochs:
current_step += 1
batch = ds.train.next_batch(mini_batch_size)
summary_str,_ , l = sess.run([merged_summary_op, train_step, cross_entropy],
feed_dict={x: batch[0], y_: batch[1], keep_prob: dropout_keep_prob})
l_sum = np.sum(l)
# skip to next epoch if loss is very small:
if l_sum < 0.001:
print('loss < 0.001. skipping to next epoch...')
curr_epoch = ds.train.epochs_completed
while curr_epoch == ds.train.epochs_completed:
ds.train.next_batch(mini_batch_size)
current_step += 1
continue
# summary_writer.add_summary(summary_str, current_step)
if current_step % 200 == 0:
train_accuracy = accuracy.eval(feed_dict={x: batch[0], y_: batch[1], keep_prob: 1.0})
y_vals = batched_eval(y_pred_sig, ds.validation.single_pass_batch_iter(1000), x, y_, keep_prob)
valid_accuracy = accuracy.eval(feed_dict={y_: ds.validation.labels, y_pred_sig: y_vals})
if best_val_acc < valid_accuracy:
saver.save(sess, save_path=path.join(chkp_dir, str(valid_accuracy)), global_step=current_step)
best_val_acc = valid_accuracy
ex.info["best_validation_accuracy"] = best_val_acc
print('run: %d, epoch: %d, iteration: %d, train accuracy: %g, validation accuracy: %g, loss: %g' %
(run_idx, ds.train.epochs_completed, current_step, train_accuracy, valid_accuracy, l_sum))
y_pred = batched_eval(y_pred_sig, ds.test.single_pass_batch_iter(1000), x, y_, keep_prob)
test_accuracy = accuracy.eval(feed_dict={y_: ds.test.labels, y_pred_sig: y_pred})
print('test accuracy: ', test_accuracy)
auc_rocs = calc_auc_rocs(ds.test.labels, y_pred)
for i, auc_roc in enumerate(auc_rocs):
print('roc-auc ' + str(i) + ":", auc_roc)
auc_rocs_weighted_sum = np.sum(np.multiply(auc_rocs, class_weights))
print('roc-auc weighted sum:', auc_rocs_weighted_sum)
ex.info["final_auc_rocs_run" + str(run_idx)] = auc_rocs
import tensorflow as tf
import numpy as np
from enhancersdata import EnhancersData
data_dir_path = '/cs/grad/pazbu/paz/dev/projects/dnanet-v2/data'
ds = EnhancersData(data_dir_path)
with tf.Session() as sess:
#First let's load meta graph and restore weights
saver = tf.train.import_meta_graph('chk-0.936961433878-120900.meta')
saver.restore(sess, tf.train.latest_checkpoint('./'))
x = tf.placeholder(tf.float32, shape=[None, 4, 1000])
y_ = tf.placeholder(tf.uint8, shape=[None, 2])
keep_prob = tf.placeholder(tf.float32)
graph = tf.get_default_graph()
y_pred_sig = graph.get_tensor_by_name("sigmoid_out:0")
correct_prediction = tf.equal(tf.argmax(y_, 1), tf.argmax(y_pred_sig, 1))
# accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
all_outcomes = []
batch_iter = ds.test.single_pass_batch_iter(100)
num_batches = np.ceil(ds.test.num_examples / 100)
c = 0
for x_batch, y_batch in batch_iter:
out = correct_prediction.eval(feed_dict={
"x:0": x_batch,
y_: y_batch,
"keep_prob:0": 1.0
