path = saver.save(sess,
checkpoint_prefix,
global_step=current_step)
print("Saved model checkpoint to {}\n".format(path))
else:
ckpt = tf.train.get_checkpoint_state(checkpoint_dir)
saver.restore(sess, ckpt.model_checkpoint_path)
accuracy, predictions = dev_step(x_test, y_test)
#dev_step(x_dev, y_dev, writer=dev_summary_writer)
outputs = np.argmax(predictions, axis=-1)
print(outputs.shape)
confusion_test = ConfusionMatrix(num_classes)
y_test = np.argmax(y_test, axis=-1)
print(y_test.shape)
confusion_test.batch_add(y_test, outputs)
test_accuracy = confusion_test.accuracy()
a, positive_predictive_value = confusion_test.positive_predictive_value()
b, negative_predictive_value = confusion_test.negative_predictive_value()
e, F1 = confusion_test.F1()
f, MCC = confusion_test.matthews_correlation()
cf_val = confusion_test.ret_mat()
print("FINAL TEST RESULTS")
print(confusion_test)
print(cf_val)
print(" test accuracy:\t\t{:.2f} %".format(test_accuracy * 100))
print(a)
print(b)
print(e)
all_y, all_preds = [], []
for i in range(n_batches_test):
x_batch = x_test[i*batch_size:(i+1)*batch_size]
y_batch = y_test[i*batch_size:(i+1)*batch_size]
probs_test, A_test = f_eval(x_batch)
preds_test_flat = probs_test.reshape((-1, num_classes)).argmax(-1)
conf_test.batch_add(
y_batch.flatten(),
preds_test_flat
)
all_y += [y_batch]
all_preds += [probs_test.argmax(-1)]
print("Epoch {} Acc Valid {}, Acc Train = {}, Acc Test = {}".format(
epoch,conf_valid.accuracy(),conf_train.accuracy(),conf_test.accuracy()))
np.savez( "res_test_3",probs=probs_test, preds=probs_test.argmax(-1),
x=x_batch, y=y_batch, A=A_test,
all_y=np.vstack(all_y),
all_preds=np.vstack(all_preds))
if conf_valid.accuracy() > best_valid:
best_valid = conf_valid.accuracy()
look_count = LOOK_AHEAD
else:
look_count -= 1
if look_count <= 0:
break
XY, XZ, YZ, Y_test = DP.Patch_triplanar_para(img, PS)
num_samples_valid = Y_test.shape[0]
num_batches_valid = num_samples_valid // batch_size
for i in range(num_batches_valid):
idx = range(i*batch_size, (i+1)*batch_size)
xy_batch = XY[idx]
xz_batch = XZ[idx]
yz_batch = YZ[idx]
targets_batch = Y_test[idx]
net_out = f_eval(xy_batch, xz_batch, yz_batch)
preds = np.argmax(net_out, axis=-1)
AB = f_vali(xy_batch, xz_batch, yz_batch, targets_batch)
confusion_valid.batch_add(targets_batch, preds)
val_loss += AB[0]/batch_size
valid_loss += [val_loss/len(Test)]
train_acc_cur = confusion_train.accuracy()
valid_acc_cur = confusion_valid.accuracy()
train_acc += [train_acc_cur]
valid_acc += [valid_acc_cur]
# if (epoch) % 10 == 0:
# np.savez('/home/xvt131/Functions/Adhish_copy/TP_param/epoch_%d_paramsBTF.npz' %(epoch), *lasagne.layers.get_all_param_values(output))
print confusion_train
print "Epoch %i : Train Loss %e , Train acc %f, Valid Loss %f, Valid acc %f " % (epoch+1, loss[-1], train_acc_cur,valid_loss[-1], valid_acc_cur)
#import Evaluation as E
np.savez('/home/xvt131/Functions/Adhish_copy/TP_param/triplanar_Params_reg.npz', *lasagne.layers.get_all_param_values(output))
x_batch = x_test[i*num_batch:(i+1)*num_batch]
y_batch = y_test[i*num_batch:(i+1)*num_batch]
probs_test, A_test = f_eval(x_batch)
preds_test_flat = probs_test.reshape((-1, num_classes)).argmax(-1)
conf_test.batch_add(
y_batch.flatten(),
preds_test_flat
)
all_y += [y_batch]
all_preds += [probs_test.argmax(-1)]
logger.info(
"Epoch {} Acc Valid {}, Acc Train = {}, Acc Test = {}".format(
epoch,
conf_valid.accuracy(),
conf_train.accuracy(),
conf_test.accuracy())
)
np.savez(os.path.join(output_folder, "res_test"),
probs=probs_test, preds=probs_test.argmax(-1),
x=x_batch, y=y_batch, A=A_test,
all_y=np.vstack(all_y),
all_preds=np.vstack(all_preds))
if conf_valid.accuracy() > best_valid:
best_valid = conf_valid.accuracy()
look_count = LOOK_AHEAD
else:
look_count -= 1
# [X_test, X_Bigs], X_post, Y_test = DP.voxel_samples(im, [9, 5])
# num_samples_valid = Y_test.shape[0]
# num_batches_valid = num_samples_valid // batch_size
# for i in range(num_batches_valid):
# idx = range(i*batch_size, (i+1)*batch_size)
# x_batch = X_test[idx]
# post_batch = X_post[idx]
# big_batch = X_Bigs[idx]
# targets_batch = Y_test[idx]
# net_out = f_eval(x_batch, post_batch, big_batch)
# preds = np.argmax(net_out, axis=-1)
# confusion_valid.batch_add(targets_batch, preds)
train_acc_cur = confusion_train.accuracy()
# valid_acc_cur = confusion_valid.accuracy()
print confusion_train
print "Epoch %i : Train Loss %e , Train acc %f, Valid acc %f " % (
epoch + 1, loss[-1], train_acc_cur, valid_acc_cur)
X, Y, Z = E.Evaluate1("/home/xvt131/Running/validating", DP.image_load, 9, 5,
f_eval)
print "Mean Gold Dice Score:", np.mean(X)
print "Mean Silver Dice Score:", np.mean(Y)
#with np.load('model.npz') as f:
#param_values = [f['arr_%d' % i] for i in range(len(f.files))]
#lasagne.layers.set_all_param_values(network, param_values)
# Full pass training set train_err = 0 train_batches = 0 confusion_train = ConfusionMatrix(n_class) # Generate minibatches and train on each one of them for batch in iterate_minibatches(X_tr, y_tr, mask_tr, batch_size, shuffle=True): inputs, targets, in_masks = batch tr_err, predict = train_fn(inputs, targets, in_masks) train_err += tr_err train_batches += 1 preds = np.argmax(predict, axis=-1) confusion_train.batch_add(targets, preds) train_loss = train_err / train_batches train_accuracy = confusion_train.accuracy() cf_train = confusion_train.ret_mat() # Full pass validation set val_err = 0 val_batches = 0 confusion_valid = ConfusionMatrix(n_class) # Generate minibatches and train on each one of them for batch in iterate_minibatches(X_val, y_val, mask_val, batch_size): inputs, targets, in_masks = batch err, predict_val, alpha, context = val_fn(inputs, targets, in_masks) val_err += err val_batches += 1 preds = np.argmax(predict_val, axis=-1)
print "Network"
print ffn
print "Loss", losslayer
print ""
acc = []
for epoch in range(num_epochs):
confusion = ConfusionMatrix(num_classes)
for i in range(num_batches):
idx = range(i*batch_size, (i+1)*batch_size)
x_batch = x_train[idx]
target_batch = targets_train[idx]
y_probs = ffn.forward(x_batch)
loss = losslayer.fprop(y_probs, target_batch)
delta = losslayer.bprop(y_probs, target_batch)
ffn.backward(delta)
ffn.update(learning_rate)
confusion.batch_add(target_batch.argmax(-1), y_probs.argmax(-1))
curr_acc = confusion.accuracy()
print "Epoch %i : Loss %f Train acc %f" % (epoch, loss, curr_acc)
acc += [curr_acc]
x_batch = x_test[i*num_batch:(i+1)*num_batch]
y_batch = y_test[i*num_batch:(i+1)*num_batch]
probs_test, A_test = f_eval(x_batch)
preds_test_flat = probs_test.reshape((-1, num_classes)).argmax(-1)
conf_test.batch_add(
y_batch.flatten(),
preds_test_flat
)
all_y += [y_batch]
all_preds += [probs_test.argmax(-1)]
logger.info(
"Epoch {} Acc Valid {}, Acc Train = {}, Acc Test = {}".format(
epoch,
conf_valid.accuracy(),
conf_train.accuracy(),
conf_test.accuracy())
)
np.savez(os.path.join(output_folder, "res_test"),
probs=probs_test, preds=probs_test.argmax(-1),
x=x_batch, y=y_batch, A=A_test,
all_y=np.vstack(all_y),
all_preds=np.vstack(all_preds))
if conf_valid.accuracy() > best_valid:
best_valid = conf_valid.accuracy()
look_count = LOOK_AHEAD
else:
look_count -= 1
