def run_for_resnet_train(): from Net.BaseNet.ResNet.resnet_train import train phase_name = 'ART' traindatapath = '/home/give/Documents/dataset/MedicalImage/MedicalImage/ROIMulti/train' valdatapath = '/home/give/Documents/dataset/MedicalImage/MedicalImage/ROIMulti/val' val_dataset = ValDataSet(new_size=[sub_Config.IMAGE_W, sub_Config.IMAGE_H], phase=phase_name, category_number=sub_Config.OUTPUT_NODE, data_path=valdatapath) train_dataset = ValDataSet( new_size=[sub_Config.IMAGE_W, sub_Config.IMAGE_H], phase=phase_name, category_number=sub_Config.OUTPUT_NODE, data_path=traindatapath) x = tf.placeholder(tf.float32, shape=[ None, sub_Config.IMAGE_W, sub_Config.IMAGE_H, sub_Config.IMAGE_CHANNEL ], name='input_x') y_ = tf.placeholder(tf.float32, shape=[ None, ]) is_training = tf.placeholder('bool', [], name='is_training') FLAGS = tf.app.flags.FLAGS tf.app.flags.DEFINE_boolean( 'use_bn', True, 'use batch normalization. otherwise use biases') logits = inference_small(x, is_training=is_training, num_classes=sub_Config.OUTPUT_NODE, use_bias=FLAGS.use_bn, num_blocks=3) train(train_generator=train_dataset, val_generator=val_dataset, logits=logits, images_tensor=x, labeles=y_)
if load_model_path: saver.restore(sess, load_model_path) validation_images, validation_labels = dataset.images, dataset.labels validation_images = changed_shape(validation_images, [ len(validation_images), sub_Config.IMAGE_W, sub_Config.IMAGE_W, 1 ]) validation_accuracy, logits = sess.run([accuracy_tensor, y], feed_dict={ x: validation_images, y_: validation_labels }) _, _, _, error_indexs, error_record = calculate_acc_error( logits=np.argmax(logits, 1), label=validation_labels, show=True) print 'accuracy is %g' % \ (validation_accuracy) return error_indexs, error_record if __name__ == '__main__': dataset = ValDataSet( data_path= '/home/give/Documents/dataset/MedicalImage/MedicalImage/ROI/val', phase='ART', new_size=[sub_Config.IMAGE_W, sub_Config.IMAGE_H], shuffle=False) error_indexs, error_record = val( dataset, load_model_path= '/home/give/PycharmProjects/MedicalImage/Net/BaseNet/LeNet/model_finetuing/model_art/', save_model_path=None) dataset.show_error_name(error_indexs, error_record)
validation_images = changed_shape(validation_images, [ len(validation_images), sub_Config.IMAGE_W, sub_Config.IMAGE_W, 1 ]) validation_accuracy, validation_loss, logits = sess.run( [accuracy_tensor, loss_, y], feed_dict={ x: validation_images, y_: validation_labels }) _, _, _, error_indexs, error_record = calculate_acc_error( logits=np.argmax(logits, 1), label=validation_labels, show=True) print 'validation loss value is %g, accuracy is %g' % \ (validation_loss, validation_accuracy) return error_indexs, error_record if __name__ == '__main__': phase_name = 'ART' state = '' val_dataset = ValDataSet( new_size=[sub_Config.IMAGE_W, sub_Config.IMAGE_H], phase=phase_name, category_number=sub_Config.OUTPUT_NODE, data_path= '/home/give/Documents/dataset/MedicalImage/MedicalImage/ROI/val') error_indexs, error_record = val( val_dataset, load_model_path= '/home/give/PycharmProjects/MedicalImage/Net/BaseNet/ResNet/models/fine_tuning/2/' ) val_dataset.show_error_name(error_indexs, error_record, copy=False)
use_bias=FLAGS.use_bn, num_blocks=3) train(train_generator=train_dataset, val_generator=val_dataset, logits=logits, images_tensor=x, labeles=y_) if __name__ == '__main__': phase_name = 'ART' state = '' traindatapath = '/home/give/Documents/dataset/MedicalImage/MedicalImage/ROIMulti/train' valdatapath = '/home/give/Documents/dataset/MedicalImage/MedicalImage/ROIMulti/val' val_dataset = ValDataSet(new_size=[sub_Config.IMAGE_W, sub_Config.IMAGE_H], phase=phase_name, category_number=sub_Config.OUTPUT_NODE, data_path=valdatapath) train_dataset = ValDataSet( new_size=[sub_Config.IMAGE_W, sub_Config.IMAGE_H], phase=phase_name, category_number=sub_Config.OUTPUT_NODE, data_path=traindatapath) train( train_dataset, val_dataset, # load_model_path='/home/give/PycharmProjects/MedicalImage/Net/BaseNet/ResNet/models/fine_tuning/5-64/21001/', load_model_path=None, save_model_path= '/home/give/PycharmProjects/MedicalImage/Net/BaseNet/ResNet/models/fine_tuning/5-64' )
label=validation_labels, ) val_writer.add_summary(summary, i) print 'step is %d,training loss value is %g, accuracy is %g ' \ 'validation loss value is %g, accuracy is %g, binary_acc is %g' % \ (i, loss_value, accuracy_value, validation_loss, validation_accuracy, binary_acc) writer.close() val_writer.close() if __name__ == '__main__': phase_name = 'ART' state = '' val_dataset = ValDataSet( new_size=[sub_Config.IMAGE_W, sub_Config.IMAGE_H], phase=phase_name, data_path='/home/give/Documents/dataset/MedicalImage/MedicalImage/ROI' + state + '/val') train_dataset = ValDataSet( new_size=[sub_Config.IMAGE_W, sub_Config.IMAGE_H], phase=phase_name, # data_path='/home/give/Documents/dataset/MedicalImage/MedicalImage/ROI' + state +'/train' data_path= '/home/give/Documents/dataset/MedicalImage/MedicalImage/ROI_Augmented/train' ) train( train_dataset, val_dataset, load_model_path=None, save_model_path= '/home/give/PycharmProjects/MedicalImage/Net/BaseNet/LeNet/model_finetuing/model_'
label=validation_labels, show=True ) val_writer.add_summary(summary, global_step_value) print 'step is %d,training loss value is %g, accuracy is %g ' \ 'validation loss value is, accuracy is %g' % \ (global_step_value, loss_value, accuracy_value, validation_accuracy) writer.close() val_writer.close() if __name__ == '__main__': phase_name = 'ART' # state = '_Expand' state = '' val_dataset = ValDataSet(new_size=[sub_Config.IMAGE_W, sub_Config.IMAGE_H], phase=phase_name, shuffle=False, category_number=sub_Config.OUTPUT_NODE, data_path='/home/give/Documents/dataset/MedicalImage/MedicalImage/ROI/val') print 'val label is ' # print val_dataset.labels train_dataset = ValDataSet(new_size=[sub_Config.IMAGE_W, sub_Config.IMAGE_H], phase=phase_name, shuffle=False, category_number=sub_Config.OUTPUT_NODE, data_path='/home/give/Documents/dataset/MedicalImage/MedicalImage/ROIMulti/train') # print np.shape(train_dataset.labels) train( train_dataset, val_dataset, # load_model_path='/home/give/PycharmProjects/MedicalImage/Net/BaseNet/LeNet/model_finetuing/2/art/', load_model_path=None,
show=True ) binary_acc = acc_binary_acc( logits=np.argmax(logits, 1), label=validation_labels, ) val_writer.add_summary(summary, i) print 'step is %d,training loss value is %g, accuracy is %g ' \ 'validation loss value is %g, accuracy is %g, binary_acc is %g' % \ (i, loss_value, accuracy_value, validation_loss, validation_accuracy, binary_acc) writer.close() val_writer.close() if __name__ == '__main__': phase_name = 'ART' state = '' val_dataset = ValDataSet(new_size=[sub_Config.IMAGE_W, sub_Config.IMAGE_H], phase=phase_name, category_number=sub_Config.OUTPUT_NODE, data_path='/home/give/Documents/dataset/MedicalImage/MedicalImage/ROI' + state +'/val') train_dataset = ValDataSet(new_size=[sub_Config.IMAGE_W, sub_Config.IMAGE_H], phase=phase_name, category_number=sub_Config.OUTPUT_NODE, data_path='/home/give/Documents/dataset/MedicalImage/MedicalImage/ROIAugmented/train' ) train( train_dataset, val_dataset, load_model_path=None, save_model_path='/home/give/PycharmProjects/MedicalImage/Net/BaseNet/LeNet/model_finetuing/model_' + phase_name.lower() + state + '/' )
label=validation_labels, ) val_writer.add_summary(summary, global_step_value) print 'step is %d,training loss value is %g, accuracy is %g ' \ 'validation loss value is %g, accuracy is %g, binary_acc is %g' % \ (global_step_value, loss_value, accuracy_value, validation_loss, validation_accuracy, binary_acc) writer.close() val_writer.close() if __name__ == '__main__': phase_name = 'ART' state = '' traindatapath = '/home/give/Documents/dataset/MedicalImage/MedicalImage/ROI/train' valdatapath = '/home/give/Documents/dataset/MedicalImage/MedicalImage/ROI/val' val_dataset = ValDataSet(new_size=[sub_Config.IMAGE_W, sub_Config.IMAGE_H], phase=phase_name, category_number=2, shuffle=True, data_path=valdatapath ) train_dataset = ValDataSet(new_size=[sub_Config.IMAGE_W, sub_Config.IMAGE_H], phase=phase_name, category_number=2, data_path=traindatapath, shuffle=True, ) train( train_dataset, val_dataset, load_model_path=None, save_model_path='/home/give/PycharmProjects/MedicalImage/Net/BaseNet/ResNet/models/fine_tuning/2-128/' )
validation_accuracy, features_value = sess.run( [accuracy_tensor, features], feed_dict={ x: validation_images, y_: validation_labels }) print validation_accuracy return features_value if __name__ == '__main__': phase = 'pv' state = 'train' dataset = ValDataSet( data_path='/home/give/Documents/dataset/MedicalImage/MedicalImage/ROI/' + state, phase=phase.upper(), new_size=[sub_Config.IMAGE_W, sub_Config.IMAGE_H], shuffle=False) features = val( dataset, load_model_path= '/home/give/PycharmProjects/MedicalImage/Net/BaseNet/LeNet/model_finetuing/model_' + phase + '/', save_model_path=None) np.save( '/home/give/PycharmProjects/MedicalImage/Net/data/' + state + '_' + phase + '.npy', features) np.save( '/home/give/PycharmProjects/MedicalImage/Net/data/' + state + '_' + phase + '_label.npy', dataset.labels) print np.shape(features)