import mimo_net
from subpackages import NetworkOptions
os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
os.environ["CUDA_VISIBLE_DEVICES"] = "1"
opts = NetworkOptions.NetworkOptions(
exp_dir=os.path.normpath(os.path.join(os.getcwd(), 'ExpDir')),
num_examples_per_epoch_train=1,
num_examples_per_epoch_valid=1,
image_height=600,
image_width=600,
label_height=600,
label_width=600,
crop_height=508,
crop_width=508,
in_feat_dim=3,
in_label_dim=4,
num_of_classes=2,
batch_size=1,
num_of_epoch=500,
data_dir=os.path.normpath(
'D:/Shan/MyCodes/TracerX/TissueSegmentation/Data'),
train_data_filename='TrainData171017.h5',
valid_data_filename='ValidData171017.h5',
current_epoch_num=0)
if os.path.isdir(os.path.join(opts.exp_dir, 'code')):
rmtree(os.path.join(opts.exp_dir, 'code'))
os.makedirs(os.path.join(opts.exp_dir, 'code'))
if not os.path.isdir(opts.exp_dir):
d[a[0]] = a[1].strip('\n')
print('results_dir: ' + d['results_dir'], flush=True)
print('file_name_pattern: ' + d['file_name_pattern'], flush=True)
print('date: ' + d['date'], flush=True)
print('exp_dir: ' + d['exp_dir'], flush=True)
opts = NetworkOptions.NetworkOptions(
exp_dir=d['exp_dir'],
num_examples_per_epoch_train=1,
num_examples_per_epoch_valid=1,
image_height=508,
image_width=508,
label_height=508,
label_width=508,
in_feat_dim=3,
in_label_dim=4,
num_of_classes=2,
batch_size=1,
data_dir=data_dir,
results_dir=d['results_dir'],
current_epoch_num=0,
file_name_pattern=d['file_name_pattern'],
pre_process=True, #False to disable matlab
)
opts.results_dir = (os.path.join(opts.results_dir, '20171031'))
if not os.path.isdir(opts.results_dir):
os.makedirs(opts.results_dir, exist_ok=True)
os.makedirs(os.path.join(opts.results_dir, 'mat'), exist_ok=True)
os.makedirs(os.path.join(opts.results_dir, 'annotated_images'),
exist_ok=True)
import sccnn_classifier as sccnn_classifier
from subpackages import NetworkOptions
# os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
# os.environ["CUDA_VISIBLE_DEVICES"] = "0"
opts = NetworkOptions.NetworkOptions(
exp_dir='ExpDir-IHC/',
num_examples_per_epoch_train=1,
num_examples_per_epoch_valid=1,
image_height=51,
image_width=51,
in_feat_dim=3,
in_label_dim=1,
num_of_classes=4,
batch_size=500,
data_dir='R:\\tracerx\\Melanoma\\Quad\\data\\cws',
results_dir='D:/tmp/results_diagostics-ihc/classification',
detection_results_path=
'R:\\tracerx\\Melanoma\\Quad\\results\\detection\\20171017',
tissue_segment_dir='',
preprocessed_dir=None,
current_epoch_num=0,
file_name_pattern='CB12*',
pre_process=True,
color_code_file='IHC_CD4_CD8_FoxP3.csv')
opts.results_dir = (os.path.join(opts.results_dir, '20171019'))
opts.preprocessed_dir = os.path.join(opts.preprocessed_dir, '20171019')
if not os.path.isdir(opts.results_dir):
os.makedirs(opts.results_dir)
print('results_dir: ' + d['results_dir'], flush=True)
print('tissue_segment_dir: ' + d['tissue_segment_dir'], flush=True)
print('file_name_pattern: ' + d['file_name_pattern'], flush=True)
print('date: ' + d['date'], flush=True)
print('exp_dir: ' + d['exp_dir'], flush=True)
opts = NetworkOptions.NetworkOptions(
exp_dir=d['exp_dir'],
num_examples_per_epoch_train=1,
num_examples_per_epoch_valid=1,
image_height=31,
image_width=31,
in_feat_dim=int(d['in_feat_dim']),
label_height=13,
label_width=13,
in_label_dim=1,
batch_size=90,
data_dir=data_dir,
results_dir=d['results_dir'],
tissue_segment_dir=d['tissue_segment_dir'],
current_epoch_num=0,
file_name_pattern=d['file_name_pattern'],
preprocessed_dir=d['preprocessed_dir'],
pre_process=True)
opts.results_dir = os.path.join(opts.results_dir, d['date'])
if d['preprocessed_dir'] is None:
opts.preprocessed_dir = os.path.join(opts.preprocessed_dir, d['date'])
if not os.path.isdir(opts.results_dir):
os.makedirs(opts.results_dir, exist_ok=True)
d[a[0]] = a[1].strip('\n')
print('exp_dir: ' + d['exp_dir'], flush=True)
print('train_data_filename:' + d['train_data_filename'], flush=True)
print('valid_data_filename:' + d['valid_data_filename'], flush=True)
opts = NetworkOptions.NetworkOptions(
exp_dir=d['exp_dir'],
num_examples_per_epoch_train=1,
num_examples_per_epoch_valid=1,
image_height=600,
image_width=600,
label_height=600,
label_width=600,
crop_height=508,
crop_width=508,
in_feat_dim=3,
in_label_dim=4,
num_of_classes=2,
batch_size=1,
num_of_epoch=500,
data_dir=data_dir,
train_data_filename=d['train_data_filename'],
valid_data_filename=d['valid_data_filename'],
current_epoch_num=0)
if os.path.isdir(os.path.join(opts.exp_dir, 'code')):
rmtree(os.path.join(opts.exp_dir, 'code'))
os.makedirs(os.path.join(opts.exp_dir, 'code'))
if not os.path.isdir(opts.exp_dir):
print('tissue_segment_dir: ' + d['tissue_segment_dir'], flush=True)
print('detection_results_path:' + d['detection_results_path'], flush=True)
print('file_name_pattern: ' + d['file_name_pattern'], flush=True)
print('date: ' + d['date'], flush=True)
print('exp_dir: ' + d['exp_dir'], flush=True)
opts = NetworkOptions.NetworkOptions(
exp_dir=d['exp_dir'],
num_examples_per_epoch_train=1,
num_examples_per_epoch_valid=1,
image_height=51,
image_width=51,
in_feat_dim=int(d['in_feat_dim']),
in_label_dim=1,
num_of_classes=int(d['num_of_classes']),
batch_size=500,
data_dir=data_dir,
results_dir=d['results_dir'],
detection_results_path=d['detection_results_path'],
tissue_segment_dir=d['tissue_segment_dir'],
preprocessed_dir=d['preprocessed_dir'],
current_epoch_num=0,
file_name_pattern=d['file_name_pattern'],
color_code_file=d['color_code_file'],
pre_process=True)
opts.results_dir = os.path.join(opts.results_dir, d['date'])
opts.preprocessed_dir = os.path.join(opts.preprocessed_dir, d['date'])
if not os.path.isdir(opts.results_dir):
os.makedirs(opts.results_dir, exist_ok=True)
import mimo_net
from subpackages import NetworkOptions
# os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
# os.environ["CUDA_VISIBLE_DEVICES"] = "1"
opts = NetworkOptions.NetworkOptions(
exp_dir='ExpDir/',
num_examples_per_epoch_train=1,
num_examples_per_epoch_valid=1,
image_height=508,
image_width=508,
label_height=508,
label_width=508,
in_feat_dim=3,
in_label_dim=4,
num_of_classes=2,
batch_size=1,
data_dir='R:\\tracerx\\Melanoma\\Quad\\data\\cws',
results_dir='R:\\tracerx\\Melanoma\\Quad\\results\\'
'tissue_segmentation',
current_epoch_num=0,
file_name_pattern='*.ndpi',
pre_process=True,
)
opts.results_dir = (os.path.join(opts.results_dir, '20171019'))
if not os.path.isdir(opts.results_dir):
os.makedirs(opts.results_dir)
os.makedirs(os.path.join(opts.results_dir, 'mat'))
os.makedirs(os.path.join(opts.results_dir, 'annotated_images'))