test_pred_full_volume_softmax1 = np.exp(test_pred_full_volume[
0, 1, :, :, :]) / (np.exp(test_pred_full_volume[0, 0, :, :, :]) +
np.exp(test_pred_full_volume[0, 1, :, :, :]))
uniqueStatsPath = '/raida/apezeshk/lung_dicom_dir/p0614/20000101/s30983/uniqueStats_p0614_20000101_s30983.mat'
uniqueStatsData = sio.loadmat(uniqueStatsPath)
noduleMask = uniqueStatsData['allMaxRadiologistMsk']
if chopVolumeFlag == 1:
noduleMaskCrop = noduleMask[300:512, 256:500, 200:300]
else:
noduleMaskCrop = noduleMask
# noduleMaskResize = np.zeros((test_pred_full_volume_softmax0.shape[0], test_pred_full_volume_softmax0.shape[1], test_pred_full_volume_softmax0.shape[2]))
# for i in range(0, test_pred_full_volume_softmax0.shape[2]):
# noduleMaskResize[:,:,i] = scipy.misc.imresize(noduleMaskCrop[:,:,i], (test_pred_full_volume_softmax0.shape[0], test_pred_full_volume_softmax0.shape[1]))
dsfactor = [
w / float(g) for w, g in zip(test_pred_full_volume_softmax0.shape,
noduleMaskCrop.shape)
]
noduleMaskResize = nd.interpolation.zoom(noduleMaskCrop.astype('float'),
zoom=dsfactor)
vol_scores0 = test_pred_full_volume_softmax0.flatten()
vol_scores1 = test_pred_full_volume_softmax1.flatten()
vol_labels = noduleMaskResize.flatten()
vol_labels = vol_labels > 0.5
vol_labels = vol_labels.astype('int')
vol_scores_all = np.hstack((vol_scores0.reshape(
(len(vol_scores0), 1)), vol_scores1.reshape((len(vol_scores1), 1))))
test_AUC, test_varAUC = SupportFuncs.Pred2AUC(vol_scores_all, vol_labels)
def Main(inputParamsConfig):
#input_shape,learning_rate, momentum, num_epochs, batchsize, data_path, train_set_size, test_set_size,
# positive_set_ratio, dropout,nonlinearityToUse,augmentation
experiment_id = str(time.strftime("%Y%m%d%H%M%S"))
input_shape = inputParamsConfig['input_shape']
learning_rate = inputParamsConfig['learning_rate']
momentum = inputParamsConfig['momentum']
num_epochs = inputParamsConfig['num_epochs']
batch_size = inputParamsConfig['batch_size']
noduleCaseFilterParams = inputParamsConfig['noduleCaseFilterParams']
data_path = inputParamsConfig['data_path']
train_set_size = inputParamsConfig['train_set_size']
test_set_size = inputParamsConfig['test_set_size']
positive_set_ratio = inputParamsConfig['positive_set_ratio']
dropout = inputParamsConfig['dropout']
nonlinearityToUse = inputParamsConfig['nonlinearityToUse']
nonlinearityToUseFC = inputParamsConfig['nonlinearityToUseFC']
numberOfLayers = inputParamsConfig['numberOfLayers']
numberOfFCUnits = inputParamsConfig['numberOfFCUnits']
numberOfFCLayers = inputParamsConfig['numberOfFCLayers']
numberOfConvFilts = inputParamsConfig['numberOfConvFilts']
filterSizeTable = inputParamsConfig['filterSizeTable']
augmentationRegularFlag = inputParamsConfig['augmentationRegularFlag']
augmentationTransformFlag = inputParamsConfig['augmentationTransformFlag']
weightInitToUse = inputParamsConfig['weightInitToUse']
lrDecayFlag = inputParamsConfig['lrDecayFlag']
biasInitVal = inputParamsConfig['biasInitVal']
fp_per_case = inputParamsConfig['fp_per_case']
phase = inputParamsConfig['phase']
discrim_shape = inputParamsConfigLocal['discrim_shape']
pos_test_size = inputParamsConfig['pos_test_size']
fp_model_to_use = inputParamsConfig['fp_model_to_use']
print(
" Learning rate: '%s' , momentum: '%s', num_epochs: '%s' ,batch size: '%s' ,data_path: '%s',Train Set Size: '%s' ,Test set Size: '%s' ,Positive set Ratio '%s' , dropout: '%s', nonlinearityToUse: '%s',augmentationRegularFlag: '%s',augmentationTransformFlag: '%s',number of layers: '%s', pos_test_size: '%s'" % (
str(learning_rate), str(momentum), str(num_epochs), str(batch_size), data_path, str(train_set_size),
str(test_set_size), str(positive_set_ratio), str(dropout), str(nonlinearityToUse), str(augmentationRegularFlag),
str(augmentationTransformFlag), str(numberOfLayers), str(pos_test_size)))
print(" Phase: '%s', Num FC Layers: '%s', Num FC Units: '%s', Number of ConvFilters: '%s'" % (str(phase), str(numberOfFCLayers), str(numberOfFCUnits), str(numberOfConvFilts)))
num_epochs=int(num_epochs)
batch_size=int(batch_size)
if phase == 'screen':
if noduleCaseFilterParams == '':
if fp_per_case == '0': #make different filenames per fp_per_case s.t. original & supplemented train set are maintained
training_filename = os.path.join('./',input_shape+'_'+str(augmentationRegularFlag)+str(augmentationTransformFlag)+'_'+str(positive_set_ratio)+'.hdf5')
else:
training_filename = os.path.join('./',input_shape+'_'+str(augmentationRegularFlag)+str(augmentationTransformFlag)+'_'+str(positive_set_ratio)
+'_fp' + fp_model_to_use + '_' + fp_per_case +'.hdf5')
else:
if fp_per_case == '0': #make different filenames per fp_per_case s.t. original & supplemented train set are maintained
training_filename = os.path.join('./',input_shape+'_'+str(augmentationRegularFlag)+str(augmentationTransformFlag)+'_'+str(positive_set_ratio)+'_filt.hdf5')
else:
training_filename = os.path.join('./',input_shape+'_'+str(augmentationRegularFlag)+str(augmentationTransformFlag)+'_'+str(positive_set_ratio)
+'_fp' + fp_model_to_use + '_' + fp_per_case +'_filt.hdf5')
elif phase == 'discrim':
if noduleCaseFilterParams == '':
training_filename = os.path.join('./',input_shape+'_'+str(augmentationRegularFlag)+str(augmentationTransformFlag)+'_'+str(positive_set_ratio)
+'_discrim' + discrim_shape.replace(' ','').replace(',','') + '_' + fp_model_to_use + '.hdf5')
else:
training_filename = os.path.join('./',input_shape+'_'+str(augmentationRegularFlag)+str(augmentationTransformFlag)+'_'+str(positive_set_ratio)
+'_discrim' + discrim_shape.replace(' ','').replace(',','') + '_' + fp_model_to_use + '_filt.hdf5')
# We save the created train and test set of size X and posetive ration r to reduce the overhead in running the pipline
if os.path.exists(training_filename):
print ("Training file already exists, reading it...")
# with h5py.File(training_filename, 'r') as data_set:
# tmp_train_set = data_set.get('train_set') # Reading list of patients and test file paths
# train_set = np.array(tmp_train_set)
# tmp_train_label = data_set.get('train_label') # Reading list of patients and test file paths
# train_label = np.array(tmp_train_label)
# tmp_test_set = data_set.get('test_set') # Reading list of patients and test file paths
# test_set = np.array(tmp_test_set)
# tmp_test_label = data_set.get('test_label') # Reading list of patients and test file paths
# test_label = np.array(tmp_test_label)
# tmp_val_set = data_set.get('val_set') # Reading list of patients and test file paths
# val_set = np.array(tmp_val_set)
# tmp_val_label = data_set.get('val_label') # Reading list of patients and test file paths
# val_label = np.array(tmp_val_label)
# tr_len_pos = len(np.where(train_label==1)[0])
# tr_len_neg = len(np.where(train_label==0)[0])
else:
inputParamsLoadData = {}
inputParamsLoadData['data_path'] = data_path
inputParamsLoadData['input_shape'] = input_shape
inputParamsLoadData['train_set_size'] = int(train_set_size)
inputParamsLoadData['test_set_size'] = int(test_set_size)
inputParamsLoadData['augmentationRegularFlag'] = int(augmentationRegularFlag)
inputParamsLoadData['augmentationTransformFlag'] = int(augmentationTransformFlag)
inputParamsLoadData['fp_per_case'] = int(fp_per_case)
inputParamsLoadData['pos_test_size'] = int(pos_test_size)
inputParamsLoadData['positive_set_ratio'] = float(positive_set_ratio)
inputParamsLoadData['fp_model_to_use'] = fp_model_to_use
inputParamsLoadData['phase'] = phase
inputParamsLoadData['discrim_shape'] = discrim_shape
inputParamsLoadData['noduleCaseFilterParams'] = noduleCaseFilterParams
inputParamsLoadData['training_filename'] = training_filename
tr_len_pos,tr_len_neg, ts_len_pos,ts_len_neg = SupportFuncs.load_data(inputParamsLoadData)
# train_set, train_label, test_set, test_label, val_set, val_label = SupportFuncs.load_data(data_path, int(train_set_size),
# int(test_set_size),
# int(augmentationFlag),float(positive_set_ratio))
# with h5py.File(training_filename, 'w') as data_set:
# #Write the dataset to a h5py file
# data_set.create_dataset('train_set', data=train_set)
# data_set.create_dataset('train_label', data=train_label)
# data_set.create_dataset('test_set', data=test_set)
# data_set.create_dataset('test_label', data=test_label)
# data_set.create_dataset('val_set', data=val_set)
# data_set.create_dataset('val_label', data=val_label)
training_file_handle = tables.open_file(training_filename, mode='r') #file closed after both train/test done
train_set = training_file_handle.root.train_set
train_label = training_file_handle.root.train_label
test_set = training_file_handle.root.test_set
test_label = training_file_handle.root.test_label
val_set = training_file_handle.root.val_set
val_label = training_file_handle.root.val_label
tr_len_pos = len(np.where(train_label[:]==1)[0]); ts_len_pos = len(np.where(test_label[:]==1)[0])
tr_len_neg = train_set.shape[0] - tr_len_pos; ts_len_neg = test_set.shape[0] - ts_len_pos
print("Train set number of positives:" + str(tr_len_pos))
print("Train set number of negatives:" + str(tr_len_neg))
if nonlinearityToUse == 'relu':
nonLinearity = lasagne.nonlinearities.rectify
elif nonlinearityToUse == 'tanh':
nonLinearity = lasagne.nonlinearities.tanh
elif nonlinearityToUse == 'sigmoid':
nonLinearity = lasagne.nonlinearities.sigmoid
else:
raise Exception(
'nonlinearityToUse: Unsupported nonlinearity type has been selected for the network, retry with a supported one!')
if nonlinearityToUseFC == 'relu':
nonLinearityFC = lasagne.nonlinearities.rectify
elif nonlinearityToUseFC == 'tanh':
nonLinearityFC = lasagne.nonlinearities.tanh
elif nonlinearityToUseFC == 'sigmoid':
nonLinearityFC = lasagne.nonlinearities.sigmoid
else:
raise Exception(
'nonlinearityToUseFC: Unsupported nonlinearity type has been selected for the network, retry with a supported one!')
biasInit = lasagne.init.Constant(biasInitVal) #for relu use biasInit=1 s.t. inputs to relu are positive in beginning
if weightInitToUse == 'normal': #according to documentation, different gains should be used depending on nonlinearity
weight_init = lasagne.init.Normal()
elif weightInitToUse == 'He':
if nonlinearityToUse=='relu':
gainToUse = np.sqrt(2)
else:
gainToUse = 1
weight_init = lasagne.init.HeNormal(gain=gainToUse)
else:
raise Exception(
'weightInitToUse: Unsupported weight initialization type has been selected, retry with a supported one!')
if lrDecayFlag==1: #if learning rate should be updated, then it has to be a shared variable
learning_rate = theano.shared(np.array(learning_rate, dtype=theano.config.floatX))
decayRate = 0.5
else:
learning_rate = float(learning_rate)
dtensor5 = T.TensorType('float32', (False,) * 5)
input_var = dtensor5('inputs')
target_var = T.ivector('targets')
inputParamsNetwork = dict(n_layer=numberOfLayers, shape=input_shape,dropout=float(dropout), nonLinearity=nonLinearity,
biasInit = biasInit, filterSizeTable = filterSizeTable, numberOfFCLayers=numberOfFCLayers,
numberOfFCUnits=numberOfFCUnits, numberOfConvFilts=numberOfConvFilts,
nonLinearityFC=nonLinearityFC)
network = Build_3dcnn(weight_init, inputParamsNetwork, input_var)
# Create a loss expression for training, i.e., a scalar objective we want
# to minimize (for our multi-class problem, it is the cross-entropy loss):
prediction = lasagne.layers.get_output(network)
loss = lasagne.objectives.categorical_crossentropy(prediction, target_var)
loss = loss.mean()
# loss=np.mean(loss)
# We could add some weight decay as well here, see lasagne.regularization.
# Create update expressions for training, i.e., how to modify the
# parameters at each training step. Here, we'll use Stochastic Gradient
# Descent (SGD) with Nesterov momentum, but Lasagne offers plenty more.
params = lasagne.layers.get_all_params(network, trainable=True)
updates = lasagne.updates.nesterov_momentum(
loss, params, learning_rate=learning_rate, momentum=float(momentum))
# Create a loss expression for validation/testing. The crucial difference
# here is that we do a deterministic forward pass through the network,
# disabling dropout layers.
test_prediction = lasagne.layers.get_output(network, deterministic=True)
test_loss = lasagne.objectives.categorical_crossentropy(test_prediction,
target_var)
# test_loss = test_loss.mean()
test_loss = test_loss.mean()
# As a bonus, also create an expression for the classification accuracy:
test_acc = T.mean(T.eq(T.argmax(test_prediction, axis=1), target_var),
dtype=theano.config.floatX)
# Compile a function performing a training step on a mini-batch (by giving
# the updates dictionary) and returning the corresponding training loss:
train_fn = theano.function([input_var, target_var], loss, updates=updates) # mode='DebugMode'
# Compile a second function computing the validation loss and accuracy:
val_fn = theano.function([input_var, target_var], [test_loss, test_acc, test_prediction]) # ,mode='DebugMode')
# Finally, launch the training loop.
print("Starting training...")
# We iterate over epochs:
for epoch in range(int(num_epochs)):
# In each epoch, we do a full pass over the training data:
train_err = 0
train_batches = 0
start_time = time.time()
for batch in Iterate_minibatches(train_set, train_label, int(batch_size), shuffle=True):
inputs, targets = batch
inputs = np.float32(inputs)
train_err += train_fn(inputs, targets)
train_batches += 1
print('learning_rate = ' + str(learning_rate.get_value()))
if lrDecayFlag == 1: #only update learning_rate if lrDecayFlag==1
if ((epoch+1) % 12) == 0:
learning_rate.set_value(decayRate * learning_rate.get_value())
# And a full pass over the validation data:
val_err = 0
val_acc = 0
val_batches = 0
all_val_pred = np.empty((0, 2),
dtype=float) # initialize; array n_samplesx2 for the 2 class predictions for all validation samples
all_val_labels = np.empty((0, 1),
dtype=float) # initialize; array n_samplesx1 for labels of all validation samples
for batch in Iterate_minibatches(val_set, val_label, int(batch_size), shuffle=False):
inputs, targets = batch
inputs = np.float32(inputs)
err, acc, val_pred = val_fn(inputs, targets)
val_err += err
val_acc += acc
val_batches += 1
all_val_pred = np.vstack((all_val_pred, val_pred))
all_val_labels = np.append(all_val_labels, targets)
val_AUC, val_varAUC = SupportFuncs.Pred2AUC(all_val_pred, all_val_labels)
# Then we print the results for this epoch:
print("Epoch {} of {} took {:.3f}s".format(
epoch + 1, num_epochs, time.time() - start_time))
print(" training loss:\t\t{:.6f}".format(train_err / train_batches))
print(" validation loss:\t\t{:.6f}".format(val_err / val_batches))
print(" validation accuracy:\t\t{:.2f} %".format(val_acc / val_batches * 100))
print(" validation AUC: " + str(val_AUC) + ", std: " + str(np.sqrt(val_varAUC)))
epoch_det[epoch + 1] = {'all_val_accuracy': (val_acc / val_batches), "all_val_loss": (val_err / val_batches),
"training_loss": (train_err / train_batches)}
all_val_accuracy.append(val_acc / val_batches)
all_val_loss.append(val_err / val_batches)
all_val_AUC.append(val_AUC)
training_loss.append(train_err / train_batches)
# After training, we compute and print the test error:
test_err = 0
test_acc = 0
test_batches = 0
all_test_pred = np.empty((0, 2),
dtype=float) # initialize; array n_samplesx2 for the 2 class predictions for all test samples
all_test_labels = np.empty((0, 1), dtype=float) # initialize; array n_samplesx1 for labels of all test samples
for batch in Iterate_minibatches(test_set, test_label, int(batch_size), shuffle=False):
inputs, targets = batch
inputs = np.float32(inputs)
err, acc, test_pred = val_fn(inputs, targets)
test_err += err
test_acc += acc
test_batches += 1
all_test_pred = np.vstack((all_test_pred, test_pred))
all_test_labels = np.append(all_test_labels, targets)
test_AUC, test_varAUC = SupportFuncs.Pred2AUC(all_test_pred, all_test_labels)
##########################################
training_file_handle.close()
##########################################
print("Final results:")
print(" test loss:\t\t\t{:.6f}".format(test_err / test_batches))
print(" test accuracy:\t\t{:.2f} %".format(
test_acc / test_batches * 100))
print("test AUC: " + str(test_AUC) + ", std: " + str(np.sqrt(test_varAUC)))
# Optionally, you could now dump the network weights to a file like this:
# np.savez('model.npz', *lasagne.layers.get_all_param_values(network))
#
# And load them again later on like this:
tmp = input_shape.replace(' ','') #get rid of space and comma in input shape
tmp = tmp.replace(',','')
filenameModel = os.path.join(model_path, 'cnn_' + tmp + '_' + experiment_id)
filenameSamples = filenameModel + '_samples'
np.savez(filenameModel, *lasagne.layers.get_all_param_values(network))
np.savez(filenameSamples, inputs=inputs, targets=targets, err=err, acc=acc, training_loss=training_loss,
test_pred=test_pred, all_test_pred=all_test_pred,all_test_labels=all_test_labels,
inputParamsConfig=inputParamsConfig, tr_len_pos = tr_len_pos, tr_len_neg = tr_len_neg,
all_val_loss=all_val_loss, all_val_accuracy=all_val_accuracy, test_AUC=test_AUC, test_varAUC=test_varAUC)
if not os.path.exists('./figures'):
os.makedirs('./figures')
fig = plt.figure()
# plt.plot(training_loss,'r',val_accuracy,'g',all_val_loss,'b')
plt.plot(training_loss, 'r', label='Training_loss=' + str("%.6f" % training_loss[num_epochs - 1]))
plt.plot(all_val_loss, 'r--', label='Val_loss=' + str("%.3f" % all_val_loss[num_epochs - 1]))
plt.plot(all_val_accuracy, 'g', label='Val_accuracy=' + str("%.3f" % all_val_accuracy[num_epochs - 1]))
plt.annotate(str("%.3f" % all_val_accuracy[num_epochs - 1]), xy=(num_epochs - 1, all_val_accuracy[num_epochs - 1]),
xytext=(num_epochs - 70, 0.6),
arrowprops=dict(facecolor='black', shrink=0.05))
plt.annotate(str("%.6f" % training_loss[num_epochs - 1]), xy=(num_epochs - 1, training_loss[num_epochs - 1]),
xytext=(num_epochs - 70, 0.3),
arrowprops=dict(facecolor='black', shrink=0.05))
plt.ylabel('Training loss and Validation accuracy')
plt.xlabel('Number of Epochs')
plt.title('Accuracy and Loss Changes')
plt.legend(fontsize=13, loc=10)
try:
fig.savefig(os.path.join(figures_path, experiment_id)) # save the figure to file
except:
Make_sure_path_exists(figures_path)
plt.close(fig)
plt.show()
# save_model(result_path, experiment_id, str(input_shape), n_layers, int(batchsize), num_epochs, momentum, learning_rate, 2
# , len(train_set), len(test_set), (test_err / test_batches), (test_acc / test_batches), test_AUC[0],
# np.sqrt(test_varAUC),augmentation)
plt.close(fig)
# plt.show()
Save_model(result_path, experiment_id, str(input_shape), numberOfLayers, int(batch_size), num_epochs, momentum,
inputParamsConfig['learning_rate'], 2
, tr_len_pos+tr_len_neg, ts_len_pos+ts_len_neg, (test_err / test_batches), (test_acc / test_batches), test_AUC[0],
np.sqrt(test_varAUC), augmentationRegularFlag, augmentationTransformFlag, nonlinearityToUse, dropout,tr_len_pos,tr_len_neg)
noduleMaskCrop.astype('float'), zoom=dsfactor)
noduleMaskResize = noduleMaskResize > 0.5
noduleMaskResize = noduleMaskResize.astype('int')
print len(np.where(noduleMaskResize == 1)[0])
vol_scores_zero = test_pred_full_volume_softmax0.flatten()
vol_scores_one = test_pred_full_volume_softmax1.flatten()
vol_scores_zero = vol_scores_zero.reshape(
len(vol_scores_zero), 1)
vol_scores_one = vol_scores_one.reshape(
len(vol_scores_one), 1)
if case_flag == 1:
vol_score = np.concatenate(
(vol_scores_zero, vol_scores_one), axis=1)
total_vol_score_tmp = np.vstack(
(total_vol_score_tmp, vol_score))
vol_scores_zoronone = np.zeros
vol_labels = noduleMaskResize.flatten()
vol_labels_tmp = np.concatenate(
(vol_labels_tmp, vol_labels), axis=0)
else:
total_vol_score_tmp = np.concatenate(
(vol_scores_zero, vol_scores_one), axis=1)
vol_scores_zoronone = np.zeros
vol_labels_tmp = noduleMaskResize.flatten()
case_flag = 1
test_AUC, test_varAUC = SupportFuncs.Pred2AUC(total_vol_score_tmp,
vol_labels_tmp.astype('int'))
print test_AUC
def Main(inputParamsConfig):
#input_shape,learning_rate, momentum, num_epochs, batchsize, data_path, train_set_size, test_set_size,
# positive_set_ratio, dropout,nonlinearityToUse,augmentation
experiment_id = str(time.strftime("%Y%m%d%H%M%S"))
input_shape = inputParamsConfig['input_shape']
learning_rate = inputParamsConfig['learning_rate']
momentum = inputParamsConfig['momentum']
num_epochs = inputParamsConfig['num_epochs']
batch_size = inputParamsConfig['batch_size']
data_path = inputParamsConfig['data_path']
train_set_size = inputParamsConfig['train_set_size']
test_set_size = inputParamsConfig['test_set_size']
positive_set_ratio = inputParamsConfig['positive_set_ratio']
dropout = inputParamsConfig['dropout']
nonlinearityToUse = inputParamsConfig['nonlinearityToUse']
numberOfLayers = inputParamsConfig['numberOfLayers']
augmentationFlag = inputParamsConfig['augmentationFlag']
print(
" Learning rate: '%s' , momentum: '%s', num_epochs: '%s' ,batch size: '%s' ,data_path: '%s' ,Train Set Size: '%s' ,Test set Size: '%s' ,Positive set Ratio '%s' , dropout: '%s', nonlinearityToUse: '%s',augmentationFlag: '%s',number of layers: '%s'"
% (str(learning_rate), str(momentum), str(num_epochs), str(batch_size),
data_path, str(train_set_size), str(test_set_size),
str(positive_set_ratio), str(dropout), str(nonlinearityToUse),
str(augmentationFlag), str(numberOfLayers)))
num_epochs = int(num_epochs)
batch_size = int(batch_size)
# We save the created train and test set of size X and posetive ration r to reduce the overhead in running the pipline
ps = []
ng = []
patient_id = []
with h5py.File(os.path.join('/diskStation/temp/test_500_0.3_28288 .hdf5'),
'r') as hf:
print('List of arrays in this file: \n', hf.keys())
tmp_test_paths = hf.get(
'Test_set') # Reading list of patients and test file paths
ps = np.array(tmp_test_paths) #full paths to all positive test patches
tmp_test_paths = hf.get('neg_test_set')
ng = np.array(tmp_test_paths)
# path_to_pos_tmp='/home/shamidian/Summer2016/DeepMed/28288/pos_28288'
# path_to_neg_tmp='/home/shamidian/Summer2016/DeepMed/28288/neg_smp_0_28288'
# for item in os.listdir(path_to_pos_tmp):
# ps.append(os.path.join(path_to_pos_tmp,item))
# for items in os.listdir(path_to_neg_tmp):
# ng.append(os.path.join(path_to_neg_tmp,items))
test_set, test_label = SupportFuncs.mat_generate_from_path(ps, ng)
#
# train_set, train_label, test_set, test_label, val_set, val_label = SupportFuncs.load_data(data_path, int(train_set_size),
# int(test_set_size),
# int(augmentationFlag),float(positive_set_ratio))
if nonlinearityToUse == 'relu':
nonLinearity = lasagne.nonlinearities.rectify
elif nonlinearityToUse == 'tanh':
nonLinearity = lasagne.nonlinearities.tanh
elif nonlinearityToUse == 'sigmoid':
nonLinearity = lasagne.nonlinearities.sigmoid
else:
raise Exception(
'nonlinearityToUse: Unsupported nonlinearity type has been selected for the network, retry with a supported one!'
)
dtensor5 = T.TensorType('float32', (False, ) * 5)
input_var = dtensor5('inputs')
target_var = T.ivector('targets')
inputParamsNetwork = dict(n_layer=numberOfLayers,
shape=input_shape,
dropout=float(dropout),
nonLinearity=nonLinearity)
network = Build_3dcnn(weight_init, inputParamsNetwork, input_var)
lasagne.layers.set_all_param_values(network, param_values)
# Create a loss expression for training, i.e., a scalar objective we want
# to minimize (for our multi-class problem, it is the cross-entropy loss):
prediction = lasagne.layers.get_output(network)
loss = lasagne.objectives.categorical_crossentropy(prediction, target_var)
loss = loss.mean()
# loss=np.mean(loss)
# We could add some weight decay as well here, see lasagne.regularization.
# Create update expressions for training, i.e., how to modify the
# parameters at each training step. Here, we'll use Stochastic Gradient
# Descent (SGD) with Nesterov momentum, but Lasagne offers plenty more.
params = lasagne.layers.get_all_params(network, trainable=True)
updates = lasagne.updates.nesterov_momentum(
loss,
params,
learning_rate=float(learning_rate),
momentum=float(momentum))
# Create a loss expression for validation/testing. The crucial difference
# here is that we do a deterministic forward pass through the network,
# disabling dropout layers.
test_prediction = lasagne.layers.get_output(network, deterministic=True)
test_loss = lasagne.objectives.categorical_crossentropy(
test_prediction, target_var)
# test_loss = test_loss.mean()
test_loss = test_loss.mean()
# As a bonus, also create an expression for the classification accuracy:
test_acc = T.mean(T.eq(T.argmax(test_prediction, axis=1), target_var),
dtype=theano.config.floatX)
# Compile a function performing a training step on a mini-batch (by giving
# the updates dictionary) and returning the corresponding training loss:
train_fn = theano.function([input_var, target_var], loss,
updates=updates) # mode='DebugMode'
# Compile a second function computing the validation loss and accuracy:
val_fn = theano.function(
[input_var, target_var],
[test_loss, test_acc, test_prediction]) # ,mode='DebugMode')
# Finally, launch the training loop.
print("Starting training...")
# We iterate over epochs:
# After training, we compute and print the test error:
test_err = 0
test_acc = 0
test_batches = 0
all_test_pred = np.empty(
(0, 2), dtype=float
) # initialize; array n_samplesx2 for the 2 class predictions for all test samples
all_test_labels = np.empty(
(0, 1), dtype=float
) # initialize; array n_samplesx1 for labels of all test samples
for batch in Iterate_minibatches(test_set,
test_label,
int(batch_size),
shuffle=False):
inputs, targets = batch
inputs = np.float32(inputs)
err, acc, test_pred = val_fn(inputs, targets)
test_err += err
test_acc += acc
test_batches += 1
all_test_pred = np.vstack((all_test_pred, test_pred))
all_test_labels = np.append(all_test_labels, targets)
test_AUC, test_varAUC = SupportFuncs.Pred2AUC(all_test_pred,
all_test_labels)
test_set_size = inputParamsConfigAll['test_set_size']
positive_set_ratio = inputParamsConfigAll['positive_set_ratio']
dropout = inputParamsConfigAll['dropout']
nonlinearityToUse = inputParamsConfigAll['nonlinearityToUse']
augmentationFlag = inputParamsConfigAll['augmentationFlag']
print(
" Learning rate: '%s' , momentum: '%s', num_epochs: '%s' ,batch size: '%s' ,data_path: '%s' ,Train Set Size: '%s' ,Test set Size: '%s' ,Positive set Ratio '%s' , dropout: '%s', nonlinearityToUse: '%s',augmentationFlag: '%s'"
% (str(learning_rate), str(momentum), str(num_epochs), str(batch_size),
data_path, str(train_set_size), str(test_set_size),
str(positive_set_ratio), str(dropout), str(nonlinearityToUse),
str(augmentationFlag)))
num_epochs = int(num_epochs)
batch_size = int(batch_size)
train_set, train_label, test_set, test_label, val_set, val_label = SupportFuncs.load_data(
data_path, int(train_set_size), int(test_set_size), int(augmentationFlag),
float(positive_set_ratio))
if nonlinearityToUse == 'relu':
nonLinearity = lasagne.nonlinearities.rectify
elif nonlinearityToUse == 'tanh':
nonLinearity = lasagne.nonlinearities.tanh
elif nonlinearityToUse == 'sigmoid':
nonLinearity = lasagne.nonlinearities.sigmoid
else:
raise Exception(
'nonlinearityToUse: Unsupported nonlinearity type has been selected for the network, retry with a supported one!'
)
dtensor5 = T.TensorType('float32', (False, ) * 5)
input_var = dtensor5('inputs')
target_var = T.ivector('targets')
savedSamplesFile = np.load(pathSavedSamples)
inputParamsConfigLocal = savedSamplesFile['inputParamsConfig'].item(
) #saved dict becomes an object, so need to turn back into dict!
screeningModelForPatches = inputParamsConfigLocal['fp_model_to_use']
masterPatchFolder = 'diskStation/LIDC/36368/screenPatches'
test_pos_paths = os.listdir(os.path.join(masterPatchFolder, 'pos'))
test_neg_paths = os.listdir(os.path.join(masterPatchFolder, 'neg'))
test_pos_paths = [
os.path.join(masterPatchFolder, 'pos', x) for x in test_pos_paths
]
test_neg_paths = [
os.path.join(masterPatchFolder, 'neg', x) for x in test_neg_paths
]
test_samples, test_labels, test_len_pos, test_len_neg = SupportFuncs.mat_generate_from_path(
test_pos_paths, test_neg_paths)
#test_samples = savedSamplesFile['inputs'] #the test samples/labels were saved in a particular order, so they can be loaded in same order
#test_labels = savedSamplesFile['targets']
#test_pred_orig = savedSamplesFile['test_pred']
########################
######Input Params######
#inputParamsConfigLocal = {}
#inputParamsConfigLocal['input_shape'] = '36, 36, 8'
#inputParamsConfigLocal['learning_rate'] = '0.04'
#inputParamsConfigLocal['momentum'] = '0.9'
#inputParamsConfigLocal['num_epochs'] = '35'
#inputParamsConfigLocal['batch_size'] = '100'
#inputParamsConfigLocal['noduleCaseFilterParams'] = 'NumberOfObservers,>=,2;IURatio,>=,0.2;SliceThicknessDicom,>=,1.5;SliceThicknessDicom,<=,3'
#inputParamsConfigLocal['train_set_size'] = '150000'
#inputParamsConfigLocal['test_set_size'] = '500'
#inputParamsConfigLocal['positive_set_ratio'] = '0.5'
filepath = folderpath + '/' + i
with open(filepath, 'rb') as csvfile:
reader = csv.reader(csvfile)
for line in reader:
train_x.append(line[0].replace('/','_'))
train_y.append(line[1])
# print the num of training/testing samples
numTrainSamples=len(train_x)
print('numTrainSamples=' + str(numTrainSamples))
numTestSamples =len(test_x)
print('numTestSamples=' + str(numTestSamples))
# read correpsonding training set
# set the name for finding the data
tr_len_pos,tr_len_neg,ts_len_pos,ts_len_neg = SupportFuncs.load_data(inputParamsLoadData)
# make sure only with those in the 9 folds
# training with tr_len_pos, tr_len_neg, ts_len_pos, ts_len_neg
training_file_handle = tables.open_file(training_filename, mode='r') #file closed after both train/test done
train_set = training_file_handle.root.train_set
train_label = training_file_handle.root.train_label
test_set = training_file_handle.root.test_set
test_label = training_file_handle.root.test_label
val_set = training_file_handle.root.val_set
val_label = training_file_handle.root.val_label
tr_len_pos = len(np.where(train_label[:]==1)[0]); ts_len_pos = len(np.where(test_label[:]==1)[0])
tr_len_neg = train_set.shape[0] - tr_len_pos; ts_len_neg = test_set.shape[0] - ts_len_pos
print("Train set number of positives:" + str(tr_len_pos))
print("Train set number of negatives:" + str(tr_len_neg))