train_op = opt.minimize(loss)
update_op = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
mav = [v for v in tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES) if 'moving_mean' in v.name]
mav = mav[0]
#with tf.control_dependencies(update_op):
# train_op = opt.minimize(loss)
sess = tf.Session()
sess.run(tf.global_variables_initializer())
#model.pretrain_load(sess)
saver = tf.train.Saver()
saver.restore(sess, save_dir + 'a.ckpt')
avg = Avg(['loss'])
for i in range(1, 1+max_iter):
x, y = get_train_pair(8)
rnd_bern = np.random.randint(100, size=[8,512,512])
rnd_bern = rnd_bern < 2
fd = {img_x: x, img_y: y, b_ph: rnd_bern}
_, _, l = sess.run([train_op, update_op, loss], fd)
avg.add(l, 0)
if i % 30 == 0:
avg.show(i)
if i % 100 == 0:
fd = {img_x: x, img_y: y}
rc, rx, ry = sess.run([recon, img_x, img_y], fd)
for k in range(rc.shape[0]):
np.save('sample_imgs/a_'+str(k)+'.npy', rc[k])
train_op = opt.minimize(loss)
update_op = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
train_step = tf.group(train_op, update_op)
acc = tf_acc(y_ph, y)
logit2 = model.get_another_logit(feature)
y2 = tf.nn.softmax(logit2)
loss2 = cross_entropy(y_ph, y2)
train_step2 = tf.train.AdamOptimizer(lr_ph, name='opt2').minimize(loss2)
acc2 = tf_acc(y_ph, y2)
sess = tf.Session()
sess.run(tf.global_variables_initializer())
avg = Avg(desc=['train acc', 'train loss', 'lr', 'test acc'])
# if args.dataset=='imgnet':
# train_data = MiniImageNet('train')
# val_data = MiniImageNet('train_val')
# if args.dataset=='cifar':
# train_data = Cifar('cifar100', 'train')
# val_data = Cifar('cifar100', 'test')
# if args.dataset=='mnist':
# train_data = MNIST('notMNIST', 'train')
# val_data = MNIST('notMNIST', 'test')
#
#
model.saver_init()
if args.from_ckpt:
model.saver_load(sess)
train_step = tf.group(train_op, update_op)
acc = tf_acc(y_ph, y)
logit2 = model.get_another_logit(feature)
y2 = tf.nn.softmax(logit2)
loss2 = cross_entropy(y_ph, y2)
opt2 = tf.train.AdamOptimizer(lr_ph, name='opt2')
train_op2 = opt2.minimize(loss2)
train_step2 = tf.group(train_op, update_op)
acc2 = tf_acc(y_ph, y2)
sess = tf.Session()
sess.run(tf.global_variables_initializer())
avg = Avg(desc=['train acc', 'train loss', 'lr', 'test acc'])
if args.dataset=='imgnet':
train_data = MiniImageNet('train')
val_data = MiniImageNet('train_val')
if args.dataset=='cifar':
train_data = Cifar('cifar100', 'train')
val_data = Cifar('cifar100', 'test')
if args.dataset=='mnist':
train_data = MNIST('notMNIST', 'train')
val_data = MNIST('notMNIST', 'test')
model.saver_init()
if args.from_ckpt:
model.saver_load(sess)
losses.append(cross_entropy(qy_ph, y))
acces.append(tf_acc(qy_ph, y))
sess = tf.Session()
sess.run(tf.global_variables_initializer())
ep_gen = []
for dset in args.test_dataset:
ep = Episode_Generator(nway, kshot, dset, phase='test_test')
ep_gen.append(ep)
for model in models:
model.saver_init()
model.saver_load(sess)
avg = Avg(desc=['train acc'])
accss = []
for i in range(5):
f_l = .0
a_l = .0
for i in range(1 + args.initial_step, 1 + args.max_iter):
rnd_dset = np.random.randint(len(ep_gen))
sx, sy, qx, qy = ep_gen[rnd_dset].next_batch(qnum)
fd = {sx_ph: sx, qx_ph: qx, qy_ph: to1hot(qy, nway)}
loss_lists = sess.run(losses, fd)
acc_lists = sess.run(acces, fd)
f_l += np.array(loss_lists)
a_l += np.array(acc_lists)
batch_size=BATCH_SIZE)
net = GAT(133, 14).to(dev)
print("TOTAL PARMS",
sum(p.numel() for p in net.parameters() if p.requires_grad))
# create optimizer
optimizer = torch.optim.Adam(net.parameters(), lr=1e-3)
dur = []
lossf = F.mse_loss
second_lossf = torch.nn.MSELoss(reduction='none')
for epoch in range(50):
net.train()
train_avg = Avg()
train2_avg = Avg()
# if epoch < 10:
for g, v in tqdm(train_loader):
optimizer.zero_grad()
if epoch >= 3:
t0 = time.time()
v = v.to(dev)
af = g.ndata['atom_features'].to(dev)
ge = g.edata['edge_features'].to(dev)
v_pred, p = net(g, af, ge)
loss = lossf(v, v_pred).mean()
loss.backward()
loss = -tf.reduce_mean(bloss * mask) * 10000
# + tf.reduce_mean( tf.abs(img_y - recon) )
#loss = tf.reduce_mean(tf.square(tf.subtract(img_y, recon)))# + tf.abs(recon))
opt = tf.train.AdamOptimizer(1e-4)
train_op = opt.minimize(loss)
update_op = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
sess = tf.Session()
sess.run(tf.global_variables_initializer())
#model.pretrain_load(sess)
saver = tf.train.Saver()
saver.restore(sess, save_dir + 'a.ckpt')
avg = Avg(['loss'])
for i in range(1, 1+max_iter):
# x, y = get_train_pair(8)
# rnd_bern = np.random.randint(100, size=[8,512,512])
# rnd_bern = rnd_bern < 2
# fd = {img_x: x, img_y: y, b_ph: rnd_bern}
# _, _, l = sess.run([train_op, update_op, loss], fd)
# p = sess.run(recon, fd)
# print (p.shape)
# avg.add(l, 0)
# if i % 30 == 0:
# avg.show(i)
if i % 10 == 0:
x, y = get_test_data(8)
fd = {img_x: x, img_y: y}
rc, rx, ry = sess.run([recon, img_x, img_y], fd)
pred = tf.reduce_sum(logits, axis=0)
acc = tf_acc(qy_ph, pred)
sess = tf.Session()
sess.run(tf.global_variables_initializer())
ep_gen = []
for dset in args.test_dataset:
ep = Episode_Generator(nway, kshot, dset, phase='test_test')
ep_gen.append(ep)
for model in models:
model.saver_init()
model.saver_load(sess)
avg = Avg(desc=['train acc'])
for j in range(5):
f_l = .0
a_l = .0
for i in range(1 + args.initial_step, 1 + args.max_iter):
rnd_dset = np.random.randint(len(ep_gen))
sx, sy, qx, qy = ep_gen[rnd_dset].next_batch(qnum)
fd = {sx_ph: sx, qx_ph: qx, qy_ph: to1hot(qy, nway)}
# loss_lists = sess.run(losses, fd)
# acc_lists = sess.run(acces, fd)
a = sess.run(acc, fd)
# print (a)
avg.add(a, 0)
avg.show(j)
out = pan.get_activation(x_1, x_2, x_3)
mask = tf.greater(y_trues, 10)
mask = tf.logical_or(mask, b_ph)
mask = tf.cast(mask, tf.float32)
loss = tf.reduce_mean((out - y_trues)**2 * mask + abs(out))
train_step = tf.train.AdamOptimizer(args.lr).minimize(loss)
sess = tf.Session()
sess.run(tf.global_variables_initializer())
saver = tf.train.Saver()
# saver.restore(sess, save_dir)
avg = Avg(desc='loss')
for i in range(1,1+args.max_iter):
x, y = get_train_pair(args.batch_size)
rnd_init = np.random.randint(100, size=2)
pn = get_patch_num(args.imsize, args.large_k, args.stride,
rnd_init[0], rnd_init[1],
args.batch_size)
rnd_bern = np.random.randint(200, size=pn)
rnd_bern = (rnd_bern < 3)
x = x[:,rnd_init[0]:,rnd_init[1]:]
y = y[:,rnd_init[0]:,rnd_init[1]:]
fd = {x_ph: x, y_ph: y, b_ph: rnd_bern}
l, _ = sess.run([loss, train_step], fd)
avg.add(l, 0)
#isTr = tf.constant(True)
isTr = True
model = Baseline_CNN(args.model_name)
y = get_proto_model_output(model, sx_ph, qx_ph, nway, isTr, trainable=True)
loss = cross_entropy(qy_ph, y)
opt = tf.train.AdamOptimizer(lr_ph)
train_op = opt.minimize(loss)
update_op = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
train_step = tf.group(train_op, update_op)
acc = tf_acc(qy_ph, y)
sess = tf.Session()
sess.run(tf.global_variables_initializer())
avg = Avg(desc=['train acc', 'train loss', 'lr'])
ep_gen = Episode_Generator(nway, kshot, args.dataset, phase='train')
model.saver_init()
if args.from_ckpt:
model.saver_load(sess)
max_step = int(500 * 64 / nway / qnum)
for j in range(args.max_epoch):
lr = 1e-3 if j < 100 else 1e-4
for i in range(max_step):
sx, sy, qx, qy = ep_gen.next_batch(qnum)
fd = {sx_ph: sx, qx_ph: qx, qy_ph: to1hot(qy, nway), lr_ph: lr}
p1, p2, _ = sess.run([acc, loss, train_step], fd)
avg.add(p1, 0)