def test(model, numerical_inputs, feature_inputs, char_inputs,
actor_char_inputs, test_labels):
max_itr = len(feature_inputs) // model.batch_size
accuracies = []
for i in range(max_itr):
numerical_input_batch = preprocess.get_batch(numerical_inputs,
i * model.batch_size,
model.batch_size)
feature_input_batch = preprocess.get_batch(feature_inputs,
i * model.batch_size,
model.batch_size)
char_input_batch = preprocess.get_batch(char_inputs,
i * model.batch_size,
model.batch_size)
actor_char_input_batch = preprocess.get_batch(actor_char_inputs,
i * model.batch_size,
model.batch_size)
label_batch = preprocess.get_batch(test_labels, i * model.batch_size,
model.batch_size)
logits = model.call(numerical_input_batch,
tf.convert_to_tensor(feature_input_batch),
char_input_batch,
actor_char_input_batch,
is_training=False)
accuracies.append(model.accuracy(logits, label_batch))
print("Testing accuracy: ", tf.reduce_mean(accuracies))
def trainEpochs(encoder,
decoder,
n_epochs,
print_every=1000,
learning_rate=0.01):
start = time.time()
print_loss_total = 0 # Reset every print_every
encoder_optimizer = optim.RMSprop(encoder.parameters(), lr=learning_rate)
decoder_optimizer = optim.RMSprop(decoder.parameters(), lr=learning_rate)
criterion = nn.NLLLoss().cuda()
for epoch in range(1, n_epochs + 1):
training_batch = get_batch(fra, eng)
input_variable = Variable(torch.LongTensor(training_batch[0])).cuda()
target_variable = Variable(torch.LongTensor(training_batch[1])).cuda()
loss = train(input_variable, target_variable, encoder, decoder,
encoder_optimizer, decoder_optimizer, criterion)
print_loss_total += loss
if epoch % print_every == 0:
print_loss_avg = print_loss_total / print_every
print_loss_total = 0
print('%s (%d %d%%) %.4f' %
(timeSince(start, epoch / n_epochs), epoch,
epoch / n_epochs * 100, print_loss_avg))
def train(model, train_inputs, train_labels):
'''
Trains the model on all of the inputs and labels for one epoch. You should shuffle your inputs
and labels - ensure that they are shuffled in the same order using tf.gather.
To increase accuracy, you may want to use tf.image.random_flip_left_right on your
inputs before doing the forward pass. You should batch your inputs.
:param model: the initialized model to use for the forward pass and backward pass
:param train_inputs: train inputs (all inputs to use for training),
shape (num_inputs, width, height, num_channels)
:param train_labels: train labels (all labels to use for training),
shape (num_labels, num_classes)
:return: Optionally list of losses per batch to use for visualize_loss
'''
num_ex, _, _, _ = train_inputs.shape
num_batches = num_ex // model.batch_size
for i in range(num_batches):
batch_inputs, batch_labels = get_batch(train_inputs, train_labels,
model.batch_size,
i * model.batch_size)
with tf.GradientTape() as tape:
predictions = model.call(batch_inputs)
loss = model.loss(predictions, batch_labels)
model.loss_list.append(loss)
gradients = tape.gradient(loss, model.trainable_variables)
model.optimizer.apply_gradients(
zip(gradients, model.trainable_variables))
print(model.accuracy(predictions, batch_labels))
return model.loss_list
def test(model, test_inputs, test_labels):
"""
Tests the model on the test inputs and labels. You should NOT randomly
flip images or do any extra preprocessing.
:param test_inputs: test data (all images to be tested),
shape (num_inputs, width, height, num_channels)
:param test_labels: test labels (all corresponding labels),
shape (num_labels, num_classes)
:return: test accuracy - this should be the average accuracy across
all batches
"""
num_ex, _, _, _ = test_inputs.shape
num_batches = num_ex // model.batch_size
accur = 0
for i in range(num_batches):
batch_inputs, batch_labels = get_batch(test_inputs, test_labels,
model.batch_size,
i * model.batch_size)
predictions = model.call(batch_inputs, is_testing=True)
a = model.accuracy(predictions, batch_labels)
print(a)
accur += a
return accur / num_batches
def test(model, encoder, epoch, num_batches):
if not os.path.exists("./output/{}".format(epoch)):
os.makedirs("./output/{}".format(epoch))
if not os.path.exists("./output/{}/0".format(epoch)):
os.makedirs("./output/{}/0".format(epoch))
l_imgs, ab_imgs = get_batch(0)
logits = model.call(l_imgs)
encoder.decode(logits, l_imgs, ab_imgs, epoch, 0)
batch_id = np.random.randint(1, num_batches - 1)
if not os.path.exists("./output/{}/{}".format(epoch, batch_id)):
os.makedirs("./output/{}/{}".format(epoch, batch_id))
l_imgs, ab_imgs = get_batch(batch_id)
logits = model.call(l_imgs)
encoder.decode(logits, l_imgs, ab_imgs, epoch, batch_id)
def test(model, test_boxes, test_size):
order = np.arange(test_size)
np.random.shuffle(order)
batch_inputs, _, order = get_batch('test', model.S, model.B, model.C, 448,
test_boxes, model.batch_size, order)
for i in range(model.batch_size):
input = batch_inputs[i]
predictions = model(tf.reshape(input, [1, 448, 448, 3]))
img = add_predictions_to_inputs(
input,
tf.reshape(predictions, [model.S, model.S, model.B * 5 + model.C]))
imwrite('./output/{}.png'.format(i), img)
def train(model, numerical_inputs, feature_inputs, char_inputs,
actor_char_inputs, train_labels):
max_itr = len(feature_inputs) // model.batch_size
losses = []
for i in range(max_itr):
print("Batch " + str(i + 1) + " / " + str(max_itr))
numerical_input_batch = preprocess.get_batch(numerical_inputs,
i * model.batch_size,
model.batch_size)
feature_input_batch = preprocess.get_batch(feature_inputs,
i * model.batch_size,
model.batch_size)
char_input_batch = preprocess.get_batch(char_inputs,
i * model.batch_size,
model.batch_size)
actor_char_input_batch = preprocess.get_batch(actor_char_inputs,
i * model.batch_size,
model.batch_size)
label_batch = preprocess.get_batch(train_labels, i * model.batch_size,
model.batch_size)
with tf.GradientTape() as tape:
logits = model.call(numerical_input_batch,
tf.convert_to_tensor(feature_input_batch),
char_input_batch,
actor_char_input_batch,
is_training=None)
loss = model.loss(logits, label_batch)
losses.append(loss)
print("Batch loss: {}".format(loss))
print("Batch accuracy: {}".format(
model.accuracy(logits, label_batch)))
gradients = tape.gradient(loss, model.trainable_variables)
model.optimizer.apply_gradients(
zip(gradients, model.trainable_variables))
return losses
def train(model, encoder, manager, num_batches):
best_loss = float("inf")
for batch_idx in range(num_batches):
print("batch {} out of {}".format(batch_idx, num_batches))
l_imgs, ab_imgs = get_batch(batch_idx)
labels = get_batch_labels(ab_imgs, encoder)
with tf.GradientTape() as tape:
logits = model.call(l_imgs)
loss = model.loss_function(logits, labels)
print("loss: {}".format(loss))
if epoch > 100 and loss < best_loss:
manager.save()
best_loss = loss
gradients = tape.gradient(loss, model.trainable_variables)
model.optimizer.apply_gradients(
zip(gradients, model.trainable_variables))
def train(model, train_boxes, train_size):
order = np.arange(train_size)
np.random.shuffle(order)
batch_num = 0
while True:
if len(order) < model.batch_size:
break
batch_inputs_list, batch_labels_list, order = get_batch(
'train', model.S, model.B, model.C, 448, train_boxes,
model.batch_size, order)
batch_inputs = tf.stack(batch_inputs_list)
batch_labels = tf.stack(batch_labels_list)
with tf.GradientTape() as tape:
predictions = model(batch_inputs)
loss = model.loss(predictions, batch_labels)
print("Loss after batch {}: {}".format(batch_num, loss))
gradients = tape.gradient(loss, model.trainable_variables)
model.optimizer.apply_gradients(
zip(gradients, model.trainable_variables))
batch_num += 1
print()
def main():
in_z = 0
volpath = os.path.join(args.datapath, 'train')
segpath = volpath
batch_size = args.batch_size
orig_dim = 256
sqr = transforms.Square()
aff = transforms.Affine()
crop = transforms.RandomCrop(224)
scale = transforms.Scale(orig_dim)
rotate = transforms.Rotate(0.5, 30)
noise = transforms.Noise(0.02)
flip = transforms.Flip()
transform_plan = [sqr, scale, aff, rotate, crop, flip, noise]
lr = 1e-4
series_names = ['Mag']
seg_series_names = ['AV']
model = models.Net23(2)
model.cuda()
optimizer = optim.RMSprop(model.parameters(), lr=lr)
out_z, center_crop_sz = utils.get_out_size(orig_dim, in_z,\
transform_plan, model)
t0 = time.time()
counter = 0
print_interval = args.log_interval
model.train()
for i in range(200000000000000000000000000000000):
weight = torch.FloatTensor([0.2, 0.8]).cuda()
vol, seg, inds = preprocess.get_batch(volpath, segpath, batch_size, in_z,\
out_z, center_crop_sz, series_names, seg_series_names,\
transform_plan, 8, nrrd=True)
vol = torch.unsqueeze(vol, 1)
vol = Variable(vol).cuda()
seg = Variable(seg).cuda()
out = model(vol).squeeze()
loss = F.cross_entropy(out, seg, weight=weight)
optimizer.zero_grad()
loss.backward()
optimizer.step()
counter += 1
sys.stdout.write('\r{:.2f}%'.format(counter * batch_size /
print_interval))
sys.stdout.flush()
if counter * batch_size >= print_interval and i > 0:
seg_hot = utils.get_hot(seg.data.cpu().numpy(), out.size()[-3])
seg_hot = np.transpose(seg_hot, axes=[1, 0, 2, 3])
out_hot = np.argmax(out.data.cpu().numpy(), axis=1)
out_hot = utils.get_hot(out_hot, out.size()[-3])
out_hot = np.transpose(out_hot, axes=[1, 0, 2, 3])
dce2 = utils.dice(seg_hot[:, 1:], out_hot[:, 1:])
vol_ind = utils.get_liver(seg)
v = vol.data.cpu().numpy()[vol_ind].squeeze()
real_seg = seg[vol_ind].data.cpu().numpy()
out_plt = out.data.cpu().numpy()[vol_ind]
out_plt = np.argmax(out_plt, axis=0)
fake_seg = out_plt
masked_real = utils.makeMask(v, real_seg, out.size()[-3], 0.5)
masked_fake = utils.makeMask(v, fake_seg, out.size()[-3], 0.5)
fig = plt.figure(1)
fig.suptitle('Volume {} ; Dice = {:.2f}'.format(\
inds[vol_ind],dce2))
v = fig.add_subplot(1, 2, 1)
v.set_title('real')
plt.imshow(masked_real)
sreal = fig.add_subplot(1, 2, 2)
sreal.set_title('fake')
plt.imshow(masked_fake)
outfile = os.path.join(args.datapath, 'out.png')
plt.savefig(outfile, dpi=200)
plt.clf()
print(('\rIteration {}: Block completed in {:.2f} sec ; Loss = {:.2f}')\
.format(i*batch_size,time.time()-t0, loss.data.cpu()[0]))
checkpoint_file = os.path.join(args.datapath,\
'model_checkpoint.pth')
torch.save(model.state_dict(), checkpoint_file)
counter = 0
t0 = time.time()
'MS': '~/Desktop/user_ml/michelle_song.1.csv',
'TH': '~/Desktop/user_ml/tony_hsieh.1.csv',
'Y': '~/Desktop/user_ml/yiyi_lyu.1.csv',
'YF': '~/Desktop/user_ml/yvonne_feng.1.csv',
#'K': '~/Desktop/user_ml/kevin_chiu.1.csv',
}
# file path of training & testing data
regular_data_file = data_files[target_name]
compare_data_files = data_files.copy()
del compare_data_files[target_name]
save_dir = "save_{}/".format(dt.datetime.now().strftime("%m%d%H%M"))
# get 'samples' train_data and 'samples' test_data and 'samples' validation data
data = preprocess.get_batch(regular_data_file, samples + samples + samples,
time_steps, step_dims)
train_data = data[:samples]
test_data = data[samples:samples * 2]
validation_data = data[samples * 2:]
# get one data for other people
cmp_data = {}
for name, file in compare_data_files.items():
cmp_data[name] = preprocess.get_batch(file, samples, time_steps, step_dims)
##### Defining graph #####
# TODO: use shape [None, time_steps, step_dims]
seq_input = tf.placeholder(tf.float32, [1, time_steps, step_dims])
encoder_inputs = tf.unstack(seq_input)
print(len(encoder_inputs),
model.cuda()
optimizer = optim.RMSprop(model.parameters(), lr=lr)
out_z, center_crop_sz = utils.get_out_size(original_size, 0,\
transform_plan, model)
t0 = time.time()
counter = 0
print_interval = 200
model.train()
weight = torch.FloatTensor([0.1, 0.45, 0.45]).cuda()
for i in range(num_steps):
vol, seg, inds = preprocess.get_batch(volpath, segpath, batch_size, 0,\
out_z, center_crop_sz, series_names, seg_series_names,\
transform_plan, 8, nrrd=True)
vol = torch.unsqueeze(vol, 1)
vol = Variable(vol).cuda()
seg = Variable(seg).cuda().long()
out = model(vol).squeeze()
loss = F.cross_entropy(out, seg, weight=weight)
optimizer.zero_grad()
loss.backward()
optimizer.step()
counter += 1
sys.stdout.write('\r{:.2f}%'.format(counter * batch_size / print_interval))
feed_dict[feed['seq_len']] = [39] * size
return feed_dict
if __name__ == '__main__':
feed, cost, train_step, decoded, ler = network(len(id_char_map) + 1)
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for i in range(100000):
size = 10
batch = get_batch(size)
feed_dict = assemble_feed(feed, size, batch)
sess.run(train_step, feed_dict=feed_dict)
if i % 10 == 9:
size = 10
batch = get_batch(size)
feed_dict = assemble_feed(feed, size, batch)
cost_result, error, result = sess.run([cost, ler, decoded],
feed_dict=feed_dict)
temp = lambda x: '_' if x == len(id_char_map) else id_char_map[
x]
str_raw = [
''.join([temp(i) for i in seq])
