def main(args): if not os.path.exists(FLAGS.checkpoint): tf.logging.fatal( 'Checkpoint %s does not exist. Have you download it? See tools/download_data.sh', FLAGS.checkpoint) g = tf.Graph() with g.as_default(): input_image = PreprocessImage(FLAGS.image_path[0]) with slim.arg_scope(inception.inception_v3_arg_scope()): logits, end_points = inception.inception_v3( input_image, num_classes=FLAGS.num_classes, is_training=False) bottleneck = end_points['PreLogits'] init_op = control_flow_ops.group( variables.initialize_all_variables(), variables.initialize_local_variables(), data_flow_ops.initialize_all_tables()) saver = tf_saver.Saver() sess = tf.Session() saver.restore(sess, FLAGS.checkpoint) # Run the evaluation on the image bottleneck_eval = np.squeeze(sess.run(bottleneck)) first = True for val in bottleneck_eval: if not first: sys.stdout.write(",") first = False sys.stdout.write('{:.3f}'.format(val)) sys.stdout.write('\n')
def build_inceptionv3_graph(images, endpoint, is_training, checkpoint, reuse=False): """Builds an InceptionV3 model graph. Args: images: A 4-D float32 `Tensor` of batch images. endpoint: String, name of the InceptionV3 endpoint. is_training: Boolean, whether or not to build a training or inference graph. checkpoint: String, path to the pretrained model checkpoint. reuse: Boolean, whether or not we are reusing the embedder. Returns: inception_output: `Tensor` holding the InceptionV3 output. inception_variables: List of inception variables. init_fn: Function to initialize the weights (if not reusing, then None). """ with slim.arg_scope(inception.inception_v3_arg_scope()): _, endpoints = inception.inception_v3( images, num_classes=1001, is_training=is_training) inception_output = endpoints[endpoint] inception_variables = slim.get_variables_to_restore() inception_variables = [ i for i in inception_variables if 'global_step' not in i.name] if is_training and not reuse: init_saver = tf.train.Saver(inception_variables) def init_fn(scaffold, sess): del scaffold init_saver.restore(sess, checkpoint) else: init_fn = None return inception_output, inception_variables, init_fn
def process_images(serialized_images): def decode(jpeg_str, central_fraction=0.875, image_size=299): decoded = tf.cast(tf.image.decode_jpeg(jpeg_str, channels=3), tf.float32) cropped = tf.image.central_crop(decoded, central_fraction=central_fraction) resized = tf.squeeze( tf.image.resize_bilinear(tf.expand_dims(cropped, [0]), [image_size, image_size], align_corners=False), [0]) resized.set_shape((image_size, image_size, 3)) normalized = tf.subtract(tf.multiply(resized, 1.0 / 127.5), 1.0) return normalized def process(images, image_size=299): images = tf.map_fn(decode, images, dtype=tf.float32) return images images = process(serialized_images) with slim.arg_scope(inception.inception_v3_arg_scope()): logits, end_points = inception.inception_v3(images, num_classes=num_classes, is_training=False) features = tf.reshape(end_points['PreLogits'], [-1, 2048]) class_predictions = tf.nn.sigmoid(logits) return features, class_predictions
def prep_graph(): global predictions global labelmap global label_dict global sess global input_image global food_list food_list = [] with open(food_names) as f: for x in f: food_list.append(x.rstrip()) g = tf.Graph() with g.as_default(): input_image = tf.placeholder(tf.string) processed_image = PreprocessImage(input_image) with slim.arg_scope(inception.inception_v3_arg_scope()): logits, end_points = inception.inception_v3(processed_image, num_classes=6012, is_training=False) predictions = end_points['multi_predictions'] = tf.nn.sigmoid( logits, name='multi_predictions') init_op = control_flow_ops.group( variables.initialize_all_variables(), variables.initialize_local_variables(), data_flow_ops.initialize_all_tables()) saver = tf_saver.Saver() sess = tf.Session() saver.restore(sess, checkpoint) labelmap, label_dict = LoadLabelMaps(6012, labelmap_file, label_dict_file)
def main(args): if not os.path.exists(FLAGS.checkpoint): tf.logging.fatal( 'Checkpoint %s does not exist. Have you download it? See tools/download_data.sh', FLAGS.checkpoint) g = tf.Graph() with g.as_default(): input_image = PreprocessImage(FLAGS.image_path[0]) with slim.arg_scope(inception.inception_v3_arg_scope()): logits, end_points = inception.inception_v3( input_image, num_classes=FLAGS.num_classes, is_training=False) bottleneck = end_points['PreLogits'] init_op = tf.group(tf.global_variables_initializer(), tf.local_variables_initializer(), tf.tables_initializer()) saver = tf_saver.Saver() sess = tf.Session() saver.restore(sess, FLAGS.checkpoint) # Run the evaluation on the image bottleneck_eval = np.squeeze(sess.run(bottleneck)) first = True for val in bottleneck_eval: if not first: sys.stdout.write(",") first = False sys.stdout.write('{:.3f}'.format(val)) sys.stdout.write('\n')
def main(args): if not os.path.exists(FLAGS.checkpoint): tf.logging.fatal( 'Checkpoint %s does not exist. Have you download it? See tools/download_data.sh', FLAGS.checkpoint) g = tf.Graph() with g.as_default(): input_image = tf.placeholder(tf.string) processed_image = PreprocessImage(input_image) with slim.arg_scope(inception.inception_v3_arg_scope()): logits, end_points = inception.inception_v3( processed_image, num_classes=FLAGS.num_classes, is_training=False) predictions = end_points['multi_predictions'] = tf.nn.sigmoid( logits, name='multi_predictions') sess = tf.Session() saver = tf_saver.Saver() logits_2 = layers.conv2d( end_points['PreLogits'], FLAGS.num_classes, [1, 1], activation_fn=None, normalizer_fn=None, scope='Conv2d_final_1x1') logits_2 = array_ops.squeeze(logits_2, [1, 2], name='SpatialSqueeze_2') predictions_2 = end_points['multi_predictions_2'] = tf.nn.sigmoid(logits_2, name='multi_predictions_2') sess.run(tf.global_variables_initializer()) saver.restore(sess, FLAGS.checkpoint)
def load(self): if self.session is None: if len(self.labelmap) != self.num_classes: logging.error( "{} lines while the number of classes is {}".format( len(self.labelmap), self.num_classes)) self.label_dict = {} for line in tf.gfile.GFile(self.dict_path).readlines(): words = [word.strip(' "\n') for word in line.split(',', 1)] self.label_dict[words[0]] = words[1] logging.warning( "Loading the network {} , first apply / query will be slower". format(self.name)) config = tf.ConfigProto() config.gpu_options.per_process_gpu_memory_fraction = self.gpu_fraction g = tf.Graph() with g.as_default(): self.input_image = tf.placeholder(tf.string) processed_image = inception_preprocess(self.input_image) with slim.arg_scope(inception.inception_v3_arg_scope()): logits, end_points = inception.inception_v3( processed_image, num_classes=self.num_classes, is_training=False) self.predictions = end_points[ 'multi_predictions'] = tf.nn.sigmoid( logits, name='multi_predictions') saver = tf_saver.Saver() self.session = tf.InteractiveSession(config=config) saver.restore(self.session, self.network_path)
def classify(self, image=None, image_path=None): #image = tf.gfile.FastGFile(image_path, 'rb').read() image_data = tf.image.decode_jpeg(image, channels=3) processed_image = inception_preprocessing.preprocess_image( image_data, inception.inception_v3.default_image_size, inception.inception_v3.default_image_size, is_training=False) processed_images = tf.expand_dims(processed_image, 0) with slim.arg_scope(inception.inception_v3_arg_scope()): logits, end_points = inception.inception_v3(processed_images, num_classes=1001, is_training=False) # In order to get probabilities we apply softmax on the output. probabilities = tf.nn.softmax(logits) init_fn = slim.assign_from_checkpoint_fn( "C:\\Users\\emman\\PycharmProjects\\TensorWebApi\\models\\inception\\inception_v3.ckpt", slim.get_model_variables('InceptionV3')) init_fn(self.session) list = [] for op in self.graph.get_operations(): for i in [ "Conv2d_1a_3x3", "Conv2d_2a_3x3", "Conv2d_2b_3x3", "MaxPool_3a_3x3", "Conv2d_3b_1x1", "Conv2d_4a_3x3", "MaxPool_5a_3x3" ]: if i in str(op.name): list.append(op) break to_graph = tf.Graph() for i in list: cg.copy_op_to_graph(org_instance=i, to_graph=to_graph, variables="") self.graph = to_graph # for a in self.graph.get_operations(): # print(str(a.name)) start_time = time.time() np_image, network_input, probabilities = self.session.run( [image_data, processed_image, probabilities]) duration = time.time() - start_time print("Compute time: " + str(duration)) probabilities = probabilities[0, 0:] return probabilities
def main(img_dir): if not os.path.exists(FLAGS.checkpoint): tf.logging.fatal( 'Checkpoint %s does not exist. Have you download it? See tools/download_data.sh', FLAGS.checkpoint) g = tf.Graph() with g.as_default(): input_image = tf.placeholder(tf.string) processed_image = PreprocessImage(input_image) with slim.arg_scope(inception.inception_v3_arg_scope()): logits, end_points = inception.inception_v3(processed_image, num_classes=FLAGS.num_classes, is_training=False) predictions = end_points['multi_predictions'] = tf.nn.sigmoid(logits, name='multi_predictions') saver = tf_saver.Saver() sess = tf.Session() saver.restore(sess, FLAGS.checkpoint) # img_dir = sorted(glob.glob(os.path.join(FLAGS.image_folder_path, '*.jpg'))) # sorted(img_dir, key = lambda d: d[-7: -4]) # Run the evaluation on the images image_path = os.path.join(FLAGS.image_folder_path, img_dir) # for i in range(len(img_dir)): # image_path = img_dir[i] if not os.path.exists(image_path): tf.logging.fatal('Input image does not exist %s', image_path) img_data = tf.gfile.FastGFile(image_path, "rb").read() print(image_path) predictions_eval = np.squeeze(sess.run(predictions, {input_image: img_data})) # Print top(n) results labelmap, label_dict = LoadLabelMaps(FLAGS.num_classes, FLAGS.labelmap, FLAGS.dict) top_k = predictions_eval.argsort()[-FLAGS.n:][::-1] label_confidence_dic = {} display_label_name = [] display_score = [] for idx in top_k: mid = labelmap[idx] display_name = label_dict.get(mid, 'unknown') score = predictions_eval[idx] label_confidence_dic[display_name] = score display_label_name.append(display_name) display_score.append(score) print('{}: {} - {} (score = {:.2f})'.format(idx, mid, display_name, score)) display_dict = dict({'name': display_label_name, 'score': display_score}) display_df = pd.DataFrame(display_dict) return display_df
def inception_net(images, num_classes, for_training=False, reuse=False): """Build Inception v3 model architecture.""" with slim.arg_scope(inception.inception_v3_arg_scope()): logits, endpoints = inception.inception_v3(images, dropout_keep_prob=0.8, num_classes=num_classes, is_training=for_training, reuse=reuse, scope='InceptionV3') return logits, endpoints
def label(image_path, checkpoint="openimages_dataset/data/2016_08/model.ckpt", num_classes=6012, labelmap_path="openimages_dataset/data/2016_08/labelmap.txt", dict_path="openimages_dataset/dict.csv", threshold=0.5, rounding_digits=1): if not os.path.exists(checkpoint): tf.logging.fatal( 'Checkpoint %s does not exist. Have you download it? See tools/download_data.sh', checkpoint) g = tf.Graph() with g.as_default(): input_image = PreprocessImage(image_path) with slim.arg_scope(inception.inception_v3_arg_scope()): logits, end_points = inception.inception_v3( input_image, num_classes=num_classes, is_training=False) predictions = end_points['multi_predictions'] = tf.nn.sigmoid( logits, name='multi_predictions') init_op = control_flow_ops.group( variables.initialize_all_variables(), variables.initialize_local_variables(), data_flow_ops.initialize_all_tables()) saver = tf_saver.Saver() config = tf.ConfigProto() config.gpu_options.allow_growth = True sess = tf.Session(config=config) saver.restore(sess, checkpoint) # Run the evaluation on the image predictions_eval = np.squeeze(sess.run(predictions)) # Print top(n) results labelmap, label_dict = LoadLabelMaps(num_classes, labelmap_path, dict_path) top_k = predictions_eval.argsort()[:][::-1] returned_labels = [] for idx in top_k: mid = labelmap[idx] display_name = label_dict.get(mid, 'unknown') score = predictions_eval[idx] if score < threshold: if returned_labels: break else: threshold -= 0.1 if threshold < 0.1: break returned_labels.append((display_name, score)) return returned_labels
def main(args): if not os.path.exists(FLAGS.checkpoint): tf.logging.fatal( 'Checkpoint %s does not exist. Have you download it? See tools/download_data.sh', FLAGS.checkpoint) g = tf.Graph() with g.as_default(): input_image = tf.placeholder(tf.string) processed_image = PreprocessImage(input_image) with slim.arg_scope(inception.inception_v3_arg_scope()): logits, end_points = inception.inception_v3( processed_image, num_classes=FLAGS.num_classes, is_training=False) predictions = end_points['multi_predictions'] = tf.nn.sigmoid( logits, name='multi_predictions') init_op = control_flow_ops.group( variables.initialize_all_variables(), variables.initialize_local_variables(), data_flow_ops.initialize_all_tables()) saver = tf_saver.Saver() sess = tf.Session() saver.restore(sess, FLAGS.checkpoint) # Run the evaluation on the images for image_path in FLAGS.image_path: if not os.path.exists(image_path): tf.logging.fatal('Input image does not exist %s', FLAGS.image_path[0]) img_data = tf.gfile.FastGFile(image_path).read() print(image_path) predictions_eval = np.squeeze( sess.run(predictions, {input_image: img_data})) # Print top(n) results labelmap, label_dict = LoadLabelMaps(FLAGS.num_classes, FLAGS.labelmap, FLAGS.dict) top_k = predictions_eval.argsort()[-FLAGS.n:][::-1] for idx in top_k: mid = labelmap[idx] display_name = label_dict.get(mid, 'unknown') score = predictions_eval[idx] print('{}: {} - {} (score = {:.2f})'.format( idx, mid, display_name, score)) print()
def load(self): if self.session is None: logging.warning("Loading the network {} , first apply / query will be slower".format(self.name)) config = tf.ConfigProto() config.gpu_options.per_process_gpu_memory_fraction = self.gpu_fraction network_path = os.path.abspath(__file__).split('annotator.py')[0]+'data/2016_08/model.ckpt' g = tf.Graph() with g.as_default(): self.input_image = tf.placeholder(tf.string) processed_image = inception_preprocess(self.input_image) with slim.arg_scope(inception.inception_v3_arg_scope()): logits, end_points = inception.inception_v3(processed_image, num_classes=self.num_classes, is_training=False) self.predictions = end_points['multi_predictions'] = tf.nn.sigmoid(logits, name='multi_predictions') saver = tf_saver.Saver() self.session = tf.InteractiveSession(config=config) saver.restore(self.session, network_path)
def load(self): if self.session is None: logging.warning("Loading the network {} , first apply / query will be slower".format(self.name)) config = tf.ConfigProto() config.gpu_options.per_process_gpu_memory_fraction = 0.15 network_path = os.path.abspath(__file__).split('annotator.py')[0]+'data/2016_08/model.ckpt' g = tf.Graph() with g.as_default(): self.input_image = tf.placeholder(tf.string) processed_image = inception_preprocess(self.input_image) with slim.arg_scope(inception.inception_v3_arg_scope()): logits, end_points = inception.inception_v3(processed_image, num_classes=self.num_classes, is_training=False) self.predictions = end_points['multi_predictions'] = tf.nn.sigmoid(logits, name='multi_predictions') saver = tf_saver.Saver() self.session = tf.InteractiveSession(config=config) saver.restore(self.session, network_path)
def _build_model(self): self.x_input = tf.placeholder(tf.float32, shape=[None, 299, 299, 3]) self.y_input = tf.placeholder(tf.int64, shape=[None]) with slim.arg_scope(inception_v3_arg_scope()): logits, _ = inception_v3(self.x_input, num_classes=1001, is_training= self.mode == 'train') self.pre_softmax = logits self.y_pred = tf.argmax(self.pre_softmax, 1) self.y_xent = tf.nn.sparse_softmax_cross_entropy_with_logits( labels=self.y_input, logits=self.pre_softmax ) self.xent = tf.reduce_sum(self.y_xent) self.correct_prediction = tf.equal(self.y_pred, self.y_input) self.num_correct = tf.reduce_sum(tf.cast(self.correct_prediction, tf.int64)) self.accuracy = tf.reduce_mean(tf.cast(self.correct_prediction, tf.float32))
def main(argv): if FLAGS.dataset == 'ifind': files = tf.data.Dataset.list_files( tf.gfile.Glob(FLAGS.data_dir + '/train/*')) dataset = files.interleave(tf.data.TFRecordDataset, cycle_length=4, block_length=16) dataset = dataset.map(_parse_function_ifind) elif FLAGS.dataset == 'kingscollege': dataset = tf.data.TFRecordDataset(FLAGS.data_dir + '/dataset_train.tfrecords') dataset = dataset.map(_parse_function_kingscollege) else: print('Invalid Option:', FLAGS.dataset) raise SystemExit dataset = dataset.repeat() dataset = dataset.shuffle(FLAGS.queue_buffer) dataset = dataset.batch(FLAGS.batch_size) image, vec, qt, AP1, AP2, AP3 = dataset.make_one_shot_iterator().get_next() # Network Definition image = tf.image.resize_images(image, size=[224, 224]) # tf.summary.image('input',image,max_outputs=30) if FLAGS.loss == 'PoseNet': y_pred, _ = inception.inception_v3(image, num_classes=7) quaternion_pred, translation_pred = tf.split(y_pred, [4, 3], axis=1) l1 = tf.nn.l2_loss(quaternion_pred - qt, name='loss/l1') l2 = tf.nn.l2_loss(translation_pred - AP2, name='loss/l2') tf.summary.scalar('PoseNet_loss/loss_quaternion', l1) tf.summary.scalar('PoseNet_loss/loss_translation', l2) loss = l1 * 500 + l2 elif FLAGS.loss == 'AP': y_pred, _ = inception.inception_v3(image, num_classes=9) AP1_pred, AP2_pred, AP3_pred = tf.split(y_pred, 3, axis=1) l1 = tf.nn.l2_loss(AP1_pred - AP1, name='loss/l1') l2 = tf.nn.l2_loss(AP2_pred - AP2, name='loss/l2') l3 = tf.nn.l2_loss(AP3_pred - AP3, name='loss/l3') tf.summary.scalar('AnchorPoints_loss/AP1', l1) tf.summary.scalar('AnchorPoints_loss/AP2', l2) tf.summary.scalar('AnchorPoints_loss/AP3', l3) loss = l1 + l2 + l3 elif FLAGS.loss == 'SE3': from se3_geodesic_loss import SE3GeodesicLoss SE3_DIM = 6 # SE3 Training Weights for KingsCollege Dataset: se3_weights = np.ones(SE3_DIM) # Default # se3_weights = np.array([0.77848403, 0.6148858 , 0.12600519, 0.00018093, 0.00020279, 0.00082466]) # KingsCollege # se3_weights = np.array([0.06126877, 0.0811294 , 0.10352387, 0.65171058, 0.73758907, 0.10090916]) # iFIND loss = SE3GeodesicLoss(se3_weights) y_pred, _ = inception.inception_v3(image, num_classes=SE3_DIM) y_pred.set_shape([FLAGS.batch_size, SE3_DIM]) y_true = tf.concat((vec, AP2), axis=1) y_true.set_shape([FLAGS.batch_size, SE3_DIM]) with tf.variable_scope('SE3_loss'): loss = loss.geodesic_loss(y_pred, y_true) else: print('Invalid Option:', FLAGS.loss) raise SystemExit tf.summary.scalar('loss', loss) # Optimiser train_op = tf.train.AdamOptimizer(FLAGS.init_lr).minimize(loss) # Session Configuration config = tf.ConfigProto( # log_device_placement=True, # allow_soft_placement=True, gpu_options=tf.GPUOptions(allow_growth=True)) saver = tf.train.Saver() with tf.Session(config=config) as sess: initializer = tf.group(tf.global_variables_initializer(), tf.local_variables_initializer()) sess.run(initializer) merged = tf.summary.merge_all() train_writer = tf.summary.FileWriter(FLAGS.model_dir + '/train', sess.graph) coord = tf.train.Coordinator() threads = tf.train.start_queue_runners(sess=sess, coord=coord) try: for step in range(FLAGS.train_iter): start_time = time.time() _, summary, loss_value = sess.run([train_op, merged, loss]) train_writer.add_summary(summary, step) duration = time.time() - start_time if step % FLAGS.log_steps == 0: examples_per_sec = FLAGS.batch_size / float(duration) format_str = ('%s: step %d, loss = %.5f ' '(%.1f examples/sec; %.3f ' 'sec/batch)') print(format_str % (datetime.now(), step, loss_value, examples_per_sec, duration)) if step % FLAGS.ckpt_steps == 0: tf.logging.log(tf.logging.INFO, 'Saving Iteration: {}'.format(step)) saver.save(sess, FLAGS.model_dir + '/iter_{}.ckpt'.format(step)) except tf.errors.OutOfRangeError: # End of dataset tf.logging.log(tf.logging.INFO, 'End of Training') except KeyboardInterrupt: tf.logging.log(tf.logging.INFO, 'Keyboard Interrupt!') finally: tf.logging.log(tf.logging.INFO, 'Stopping Threads') coord.request_stop() coord.join(threads) tf.logging.log(tf.logging.INFO, 'Saving iter: {}'.format(step)) saver.save(sess, FLAGS.model_dir + '/iter_{}.ckpt'.format(step))
# create a list of all our filenames filename_train = ['../dataset/KingsCollege/dataset_train.tfrecords'] #filename_test = ['../dataset/KingsCollege/dataset_test.tfrecords'] reader_train = PoseNetReader(filename_train) #reader_eval = PoseNetReader(filename_test) # Get Input Tensors image, pose_q, pose_x = reader_train.read_and_decode() #image, pose_q, pose_x = reader_eval.read_and_decode() # Construct model and encapsulating all ops into scopes, making # Tensorboard's Graph visualization more convenient with tf.name_scope('Model'): py_x , _ = inception.inception_v3(tf.cast(image,tf.float32)) py_x = tf.nn.relu(py_x) weights = { 'h1': tf.Variable(tf.random_normal([1000, 4]),name='w_wpqr_out'), 'h2': tf.Variable(tf.random_normal([1000, 3]),name='w_xyz_out'), } biases = { 'b1': tf.Variable(tf.zeros([4]),name='b_wpqr_out'), 'b2': tf.Variable(tf.zeros([3]),name='b_xyz_out'), } cls3_fc_pose_wpqr = tf.add(tf.matmul(py_x, weights['h1']), biases['b1']) cls3_fc_pose_xyz = tf.add(tf.matmul(py_x, weights['h2']), biases['b2'])
# create a list of all our filenames #filename_train = ['dataset/KingsCollege/dataset_train.tfrecords'] filename_test = ['../dataset/KingsCollege/dataset_test.tfrecords'] #reader_train = PoseNetReader(filename_train) reader_eval = PoseNetReader(filename_test) # Get Input Tensors #image, pose_q, pose_x = reader_train.read_and_decode() image, pose_q, pose_x = reader_eval.read_and_decode() # Construct model and encapsulating all ops into scopes, making # Tensorboard's Graph visualization more convenient with tf.name_scope('Model'): py_x, _ = inception.inception_v3(tf.cast(image, tf.float32), is_training=False) py_x = tf.nn.relu(py_x) weights = { 'h1': tf.Variable(tf.random_normal([1000, 4]), name='w_wpqr_out'), 'h2': tf.Variable(tf.random_normal([1000, 3]), name='w_xyz_out'), } biases = { 'b1': tf.Variable(tf.random_normal([4]), name='b_wpqr_out'), 'b2': tf.Variable(tf.random_normal([3]), name='b_xyz_out'), } cls3_fc_pose_wpqr = tf.add(tf.matmul(py_x, weights['h1']), biases['b1']) cls3_fc_pose_xyz = tf.add(tf.matmul(py_x, weights['h2']), biases['b2'])
def main(argv): # TF Record datafiles = FLAGS.data_dir + '/test/' + FLAGS.subject_id + '.tfrecord' dataset = tf.data.TFRecordDataset(datafiles) dataset = dataset.map(_parse_function_ifind) # dataset = dataset.repeat() # dataset = dataset.shuffle(FLAGS.queue_buffer) dataset = dataset.batch(1) image, vec, qt, AP1, AP2, AP3 = dataset.make_one_shot_iterator().get_next() # Nifti Volume subject_path = FLAGS.scan_dir + '/test/' + FLAGS.subject_id + '.nii.gz' fixed_image_sitk_tmp = sitk.ReadImage(subject_path, sitk.sitkFloat32) fixed_image_sitk = sitk.GetImageFromArray( sitk.GetArrayFromImage(fixed_image_sitk_tmp)) fixed_image_sitk = sitk.RescaleIntensity(fixed_image_sitk, 0, 1) * 255. # Network Definition image_resized = tf.image.resize_images(image, size=[224, 224]) # Measurements cc = [] mse = [] psnr = [] ssim = [] if FLAGS.loss == 'PoseNet': y_pred, _ = inception.inception_v3(image_resized, num_classes=7, is_training=False) quaternion_pred, translation_pred = tf.split(y_pred, [4, 3], axis=1) sess = tf.Session() ckpt_file = tf.train.latest_checkpoint(FLAGS.model_dir) tf.train.Saver().restore(sess, ckpt_file) print('restoring parameters from', ckpt_file) SO3_GROUP = SpecialOrthogonalGroup(3) for i in tqdm.tqdm(range(FLAGS.n_iter)): _image, _quaternion_true, _translation_true, _quaternion_pred, _translation_pred = \ sess.run([image, qt, AP2, quaternion_pred, translation_pred]) rx = SO3_GROUP.matrix_from_quaternion(_quaternion_pred)[0] tx = _translation_pred[0] * 60. image_true = np.squeeze(_image) image_pred = resample_sitk(fixed_image_sitk, rx, tx) imageio.imsave('imgdump/image_{}_true.png'.format(i), np.uint8(_image[0, ...])) imageio.imsave('imgdump/image_{}_pred.png'.format(i), np.uint8(image_pred)) cc.append(calc_correlation(image_pred, image_true)) mse.append(calc_mse(image_pred, image_true)) psnr.append(calc_psnr(image_pred, image_true)) ssim.append(calc_ssim(image_pred, image_true)) elif FLAGS.loss == 'AP': y_pred, _ = inception.inception_v3(image_resized, num_classes=9, is_training=False) AP1_pred, AP2_pred, AP3_pred = tf.split(y_pred, 3, axis=1) sess = tf.Session() ckpt_file = tf.train.latest_checkpoint(FLAGS.model_dir) tf.train.Saver().restore(sess, ckpt_file) print('restoring parameters from', ckpt_file) for i in tqdm.tqdm(range(FLAGS.n_iter)): _image, _AP1, _AP2, _AP3, _AP1_pred, _AP2_pred, _AP3_pred = \ sess.run([image, AP1, AP2, AP3, AP1_pred, AP2_pred, AP3_pred]) dist_ap1 = np.linalg.norm(_AP1 - _AP1_pred) dist_ap2 = np.linalg.norm(_AP2 - _AP2_pred) dist_ap3 = np.linalg.norm(_AP3 - _AP3_pred) rx = matrix_from_anchor_points(_AP1_pred[0], _AP2_pred[0], _AP3_pred[0]) tx = _AP2_pred[0] * 60. image_true = np.squeeze(_image) image_pred = resample_sitk(fixed_image_sitk, rx, tx) imageio.imsave('imgdump/image_{}_true.png'.format(i), np.uint8(_image[0, ...])) imageio.imsave('imgdump/image_{}_pred.png'.format(i), np.uint8(image_pred)) cc.append(calc_correlation(image_pred, image_true)) mse.append(calc_mse(image_pred, image_true)) psnr.append(calc_psnr(image_pred, image_true)) ssim.append(calc_ssim(image_pred, image_true)) elif FLAGS.loss == 'SE3': y_pred, _ = inception.inception_v3(image_resized, num_classes=6, is_training=False) sess = tf.Session() ckpt_file = tf.train.latest_checkpoint(FLAGS.model_dir) tf.train.Saver().restore(sess, ckpt_file) print('restoring parameters from', ckpt_file) SO3_GROUP = SpecialOrthogonalGroup(3) SE3_GROUP = SpecialEuclideanGroup(3) _se3_err_i = [] for i in tqdm.tqdm(range(FLAGS.n_iter)): _image, _rvec, _tvec, _y_pred = \ sess.run([image, vec, AP2, y_pred]) rx = SO3_GROUP.matrix_from_rotation_vector(_y_pred[0, :3])[0] tx = _y_pred[0, 3:] * 60. image_true = np.squeeze(_image) image_pred = resample_sitk(fixed_image_sitk, rx, tx) imageio.imsave('imgdump/image_{}_true.png'.format(i), np.uint8(_image[0, ...])) imageio.imsave('imgdump/image_{}_pred.png'.format(i), np.uint8(image_pred)) cc.append(calc_correlation(image_pred, image_true)) mse.append(calc_mse(image_pred, image_true)) psnr.append(calc_psnr(image_pred, image_true)) ssim.append(calc_ssim(image_pred, image_true)) _y_true = np.concatenate((_rvec, _tvec), axis=-1) _se3_err_i.append( SE3_GROUP.compose(SE3_GROUP.inverse(_y_true), _y_pred)) err_vec = np.vstack(_se3_err_i) err_weights = np.diag(np.linalg.inv(np.cov(err_vec.T))) err_weights = err_weights / np.linalg.norm(err_weights) print(err_weights) else: print('Invalid Option:', FLAGS.loss) raise SystemExit cc = np.stack(cc) mse = np.stack(mse) psnr = np.stack(psnr) ssim = np.stack(ssim) print('CC:', np.median(cc)) print('MSE:', np.median(mse)) print('PSNR:', np.median(psnr)) print('SSIM:', np.median(ssim))
checkpoint='data/2016_08/model.ckpt' labelmap='data/2016_08/labelmap.txt' dict='dict.csv' image_size=299 num_classes=6012 n=10 g = tf.Graph() with g.as_default(): input_image = tf.placeholder(tf.float32,shape=[None,299,299,3]) #processed_image = PreprocessImage(input_image,image_size) processed_image=input_image with slim.arg_scope(inception.inception_v3_arg_scope()): logits, end_points = inception.inception_v3( processed_image, num_classes=num_classes, is_training=False) predictions = end_points['multi_predictions'] = tf.nn.sigmoid( logits, name='multi_predictions') saver = tf_saver.Saver() sess = tf.Session() saver.restore(sess, checkpoint) def classify(images): # embedding=np.empty([len(images),1000]) with g.as_default(): embedding=[] # Run the evaluation on the image # print(images_x_x)
def main(argv): # TF Record datafiles = FLAGS.data_dir + '/test/' + FLAGS.subject_id + '.tfrecord' dataset = tf.data.TFRecordDataset(datafiles) dataset = dataset.map(_parse_function_ifind) # dataset = dataset.repeat() # dataset = dataset.shuffle(FLAGS.queue_buffer) dataset = dataset.batch(1) image, vec, qt, AP1, AP2, AP3 = dataset.make_one_shot_iterator().get_next() # Nifti Volume subject_path = FLAGS.scan_dir + '/test/' + FLAGS.subject_id + '.nii.gz' fixed_image_sitk_tmp = sitk.ReadImage(subject_path, sitk.sitkFloat32) fixed_image_sitk = sitk.GetImageFromArray( sitk.GetArrayFromImage(fixed_image_sitk_tmp)) fixed_image_sitk = sitk.RescaleIntensity(fixed_image_sitk, 0, 1) # * 255. # Network Definition image_input = tf.placeholder(shape=[1, 224, 224, 1], dtype=tf.float32) image_resized = tf.image.resize_images(image, size=[224, 224]) if FLAGS.loss == 'PoseNet': y_pred, _ = inception.inception_v3(image_input, num_classes=7) quaternion_pred, translation_pred = tf.split(y_pred, [4, 3], axis=1) sess = tf.Session() ckpt_file = tf.train.latest_checkpoint(FLAGS.model_dir) tf.train.Saver().restore(sess, ckpt_file) print('restoring parameters from', ckpt_file) SO3_GROUP = SpecialOrthogonalGroup(3) for i in range(FLAGS.n_iter): _image, _image_resized, _quaternion_true, _translation_true = \ sess.run([image, image_resized, qt, AP2], ) _quaternion_pred_sample = [] _translation_pred_sample = [] for j in range(FLAGS.n_samples): _quaternion_pred_i, _translation_pred_i = \ sess.run([quaternion_pred, translation_pred], feed_dict={image_input: _image_resized}) _quaternion_pred_sample.append(_quaternion_pred_i) _translation_pred_sample.append(_translation_pred_i) print(_quaternion_pred_i, _translation_pred_i) _quaternion_pred_sample = np.vstack(_quaternion_pred_sample) _rotvec_pred_sample = SO3_GROUP.rotation_vector_from_quaternion( _quaternion_pred_sample) _rotvec_pred = SO3_GROUP.left_canonical_metric.mean( _rotvec_pred_sample) _quaternion_pred = SO3_GROUP.quaternion_from_rotation_vector( _rotvec_pred) _translation_pred = np.mean(np.vstack(_translation_pred_sample), axis=0) # _quaternion_pred_variance = SO3_GROUP.left_canonical_metric.variance(_rotvec_pred_sample) _translation_pred_variance = np.var( np.vstack(_translation_pred_sample), axis=0) rx = SO3_GROUP.matrix_from_quaternion(_quaternion_pred)[0] tx = _translation_pred[0] * 60. image_true = np.squeeze(_image) image_pred = resample_sitk(fixed_image_sitk, rx, tx) imageio.imsave('imgdump/image_{}_true.png'.format(i), _image[0, ...]) imageio.imsave('imgdump/image_{}_pred.png'.format(i), image_pred) calc_psnr(image_pred, image_true) calc_mse(image_pred, image_true) calc_ssim(image_pred, image_true) calc_correlation(image_pred, image_true) elif FLAGS.loss == 'AP': y_pred, _ = inception.inception_v3(image_input, num_classes=9) AP1_pred, AP2_pred, AP3_pred = tf.split(y_pred, 3, axis=1) sess = tf.Session() ckpt_file = tf.train.latest_checkpoint(FLAGS.model_dir) tf.train.Saver().restore(sess, ckpt_file) print('restoring parameters from', ckpt_file) for i in range(FLAGS.n_iter): _image, _image_resized, _AP1, _AP2, _AP3 = \ sess.run([image, image_resized, AP1, AP2, AP3]) _AP1_sample = [] _AP2_sample = [] _AP3_sample = [] for j in range(FLAGS.n_samples): _AP1_pred_i, _AP2_pred_i, _AP3_pred_i = \ sess.run([AP1_pred, AP2_pred, AP3_pred], feed_dict={image_input: _image_resized}) _AP1_sample.append(_AP1_pred_i) _AP2_sample.append(_AP2_pred_i) _AP3_sample.append(_AP3_pred_i) _AP1_pred = np.mean(np.vstack(_AP1_sample), axis=0) _AP2_pred = np.mean(np.vstack(_AP2_sample), axis=0) _AP3_pred = np.mean(np.vstack(_AP3_sample), axis=0) _AP1_pred_variance = np.var(np.vstack(_AP1_sample), axis=0) _AP2_pred_variance = np.var(np.vstack(_AP2_sample), axis=0) _AP3_pred_variance = np.var(np.vstack(_AP3_sample), axis=0) dist_ap1 = np.linalg.norm(_AP1 - _AP1_pred) dist_ap2 = np.linalg.norm(_AP2 - _AP2_pred) dist_ap3 = np.linalg.norm(_AP3 - _AP3_pred) rx = matrix_from_anchor_points(_AP1_pred[0], _AP2_pred[0], _AP3_pred[0]) tx = _AP2_pred[0] * 60. image_true = np.squeeze(_image) image_pred = resample_sitk(fixed_image_sitk, rx, tx) imageio.imsave('imgdump/image_{}_true.png'.format(i), _image[0, ...]) imageio.imsave('imgdump/image_{}_pred.png'.format(i), image_pred) calc_psnr(image_pred, image_true) calc_mse(image_pred, image_true) calc_ssim(image_pred, image_true) calc_correlation(image_pred, image_true) elif FLAGS.loss == 'SE3': y_pred, _ = inception.inception_v3(image_input, num_classes=6) sess = tf.Session() ckpt_file = tf.train.latest_checkpoint(FLAGS.model_dir) tf.train.Saver().restore(sess, ckpt_file) print('restoring parameters from', ckpt_file) SO3_GROUP = SpecialOrthogonalGroup(3) SE3_GROUP = SpecialEuclideanGroup(3) for i in range(FLAGS.n_iter): print(i) _image, _image_resized, _rvec, _tvec = \ sess.run([image, image_resized, vec, AP2]) _y_pred_sample = [] for j in range(FLAGS.n_samples): _y_pred_i = sess.run([y_pred], feed_dict={image_input: _image_resized}) _y_pred_sample.append(_y_pred_i[0]) _y_pred_sample = np.vstack(_y_pred_sample) _y_pred = SE3_GROUP.left_canonical_metric.mean(_y_pred_sample) _y_pred_variance = SE3_GROUP.left_canonical_metric.variance( _y_pred_sample) rx = SO3_GROUP.matrix_from_rotation_vector(_y_pred[0, :3])[0] tx = _y_pred[0, 3:] * 60. image_true = np.squeeze(_image) image_pred = resample_sitk(fixed_image_sitk, rx, tx) imageio.imsave('imgdump/image_{}_true.png'.format(i), _image[0, ...]) imageio.imsave('imgdump/image_{}_pred.png'.format(i), image_pred) calc_psnr(image_pred, image_true) calc_mse(image_pred, image_true) calc_ssim(image_pred, image_true) calc_correlation(image_pred, image_true) else: print('Invalid Option:', FLAGS.loss) raise SystemExit
from tensorflow.contrib.slim.python.slim.nets import inception from tensorflow.python.training import saver as tf_saver from tensorflow.python.framework import graph_util slim = tf.contrib.slim input_checkpoint = '/home/johnny/Documents/TF_CONFIG/finetune/resv2/model.ckpt' output_file = 'inference_graph.pb' g = tf.Graph() with g.as_default(): image = tf.placeholder(name='input', dtype=tf.float32, shape=[1, 299, 299, 3]) with slim.arg_scope(inception.inception_v3_arg_scope()): logits, end_points = inception.inception_v3(image, num_classes=6012, is_training=False) predictions = tf.nn.sigmoid(logits, name='multi_predictions') saver = tf_saver.Saver() input_graph_def = g.as_graph_def() sess = tf.Session() saver.restore(sess, input_checkpoint) output_node_names = "multi_predictions" output_graph_def = graph_util.convert_variables_to_constants( sess, # The session is used to retrieve the weights input_graph_def, # The graph_def is used to retrieve the nodes output_node_names.split( "," ) # The output node names are used to select the usefull nodes )
def VAE(input_shape=[None, 784], output_shape=[None, 784], n_filters=[64, 64, 64], filter_sizes=[4, 4, 4], n_hidden=32, n_code=2, activation=tf.nn.tanh, dropout=False, denoising=False, convolutional=False, variational=False, softmax=False, classifier='alexnet_v2'): """(Variational) (Convolutional) (Denoising) Autoencoder. Uses tied weights. Parameters ---------- input_shape : list, optional Shape of the input to the network. e.g. for MNIST: [None, 784]. n_filters : list, optional Number of filters for each layer. If convolutional=True, this refers to the total number of output filters to create for each layer, with each layer's number of output filters as a list. If convolutional=False, then this refers to the total number of neurons for each layer in a fully connected network. filter_sizes : list, optional Only applied when convolutional=True. This refers to the ksize (height and width) of each convolutional layer. n_hidden : int, optional Only applied when variational=True. This refers to the first fully connected layer prior to the variational embedding, directly after the encoding. After the variational embedding, another fully connected layer is created with the same size prior to decoding. Set to 0 to not use an additional hidden layer. n_code : int, optional Only applied when variational=True. This refers to the number of latent Gaussians to sample for creating the inner most encoding. activation : function, optional Activation function to apply to each layer, e.g. tf.nn.relu dropout : bool, optional Whether or not to apply dropout. If using dropout, you must feed a value for 'keep_prob', as returned in the dictionary. 1.0 means no dropout is used. 0.0 means every connection is dropped. Sensible values are between 0.5-0.8. denoising : bool, optional Whether or not to apply denoising. If using denoising, you must feed a value for 'corrupt_rec', as returned in the dictionary. 1.0 means no corruption is used. 0.0 means every feature is corrupted. Sensible values are between 0.5-0.8. convolutional : bool, optional Whether or not to use a convolutional network or else a fully connected network will be created. This effects the n_filters parameter's meaning. variational : bool, optional Whether or not to create a variational embedding layer. This will create a fully connected layer after the encoding, if `n_hidden` is greater than 0, then will create a multivariate gaussian sampling layer, then another fully connected layer. The size of the fully connected layers are determined by `n_hidden`, and the size of the sampling layer is determined by `n_code`. Returns ------- model : dict { 'cost': Tensor to optimize. 'Ws': All weights of the encoder. 'x': Input Placeholder 'z': Inner most encoding Tensor (latent features) 'y': Reconstruction of the Decoder 'keep_prob': Amount to keep when using Dropout 'corrupt_rec': Amount to corrupt when using Denoising 'train': Set to True when training/Applies to Batch Normalization. } """ # network input / placeholders for train (bn) and dropout x = tf.placeholder(tf.float32, input_shape, 'x') t = tf.placeholder(tf.float32, output_shape, 't') label = tf.placeholder(tf.int32, [None], 'label') phase_train = tf.placeholder(tf.bool, name='phase_train') keep_prob = tf.placeholder(tf.float32, name='keep_prob') corrupt_rec = tf.placeholder(tf.float32, name='corrupt_rec') corrupt_cls = tf.placeholder(tf.float32, name='corrupt_cls') # input of the reconstruction network # np.tanh(2) = 0.964 current_input1 = utils.corrupt(x)*corrupt_rec + x*(1-corrupt_rec) \ if (denoising and phase_train is not None) else x current_input1.set_shape(x.get_shape()) # 2d -> 4d if convolution current_input1 = utils.to_tensor(current_input1) \ if convolutional else current_input1 Ws = [] shapes = [] # Build the encoder for layer_i, n_output in enumerate(n_filters): with tf.variable_scope('encoder/{}'.format(layer_i)): shapes.append(current_input1.get_shape().as_list()) if convolutional: h, W = utils.conv2d(x=current_input1, n_output=n_output, k_h=filter_sizes[layer_i], k_w=filter_sizes[layer_i]) else: h, W = utils.linear(x=current_input1, n_output=n_output) h = activation(batch_norm(h, phase_train, 'bn' + str(layer_i))) if dropout: h = tf.nn.dropout(h, keep_prob) Ws.append(W) current_input1 = h shapes.append(current_input1.get_shape().as_list()) with tf.variable_scope('variational'): if variational: dims = current_input1.get_shape().as_list() flattened = utils.flatten(current_input1) if n_hidden: h = utils.linear(flattened, n_hidden, name='W_fc')[0] h = activation(batch_norm(h, phase_train, 'fc/bn')) if dropout: h = tf.nn.dropout(h, keep_prob) else: h = flattened z_mu = utils.linear(h, n_code, name='mu')[0] z_log_sigma = 0.5 * utils.linear(h, n_code, name='log_sigma')[0] # modified by yidawang # s, u, v = tf.svd(z_log_sigma) # z_log_sigma = tf.matmul( # tf.matmul(u, tf.diag(s)), tf.transpose(v)) # end yidawang # Sample from noise distribution p(eps) ~ N(0, 1) epsilon = tf.random_normal(tf.stack([tf.shape(x)[0], n_code])) # Sample from posterior z = z_mu + tf.multiply(epsilon, tf.exp(z_log_sigma)) if n_hidden: h = utils.linear(z, n_hidden, name='fc_t')[0] h = activation(batch_norm(h, phase_train, 'fc_t/bn')) if dropout: h = tf.nn.dropout(h, keep_prob) else: h = z size = dims[1] * dims[2] * dims[3] if convolutional else dims[1] h = utils.linear(h, size, name='fc_t2')[0] current_input1 = activation(batch_norm(h, phase_train, 'fc_t2/bn')) if dropout: current_input1 = tf.nn.dropout(current_input1, keep_prob) if convolutional: current_input1 = tf.reshape( current_input1, tf.stack([ tf.shape(current_input1)[0], dims[1], dims[2], dims[3] ])) else: z = current_input1 shapes.reverse() n_filters.reverse() Ws.reverse() n_filters += [input_shape[-1]] # %% # Decoding layers for layer_i, n_output in enumerate(n_filters[1:]): with tf.variable_scope('decoder/{}'.format(layer_i)): shape = shapes[layer_i + 1] if convolutional: h, W = utils.deconv2d(x=current_input1, n_output_h=shape[1], n_output_w=shape[2], n_output_ch=shape[3], n_input_ch=shapes[layer_i][3], k_h=filter_sizes[layer_i], k_w=filter_sizes[layer_i]) else: h, W = utils.linear(x=current_input1, n_output=n_output) h = activation(batch_norm(h, phase_train, 'dec/bn' + str(layer_i))) if dropout: h = tf.nn.dropout(h, keep_prob) current_input1 = h y = current_input1 t_flat = utils.flatten(t) y_flat = utils.flatten(y) # l2 loss loss_x = tf.reduce_mean( tf.reduce_sum(tf.squared_difference(t_flat, y_flat), 1)) loss_z = 0 if variational: # Variational lower bound, kl-divergence loss_z = tf.reduce_mean(-0.5 * tf.reduce_sum( 1.0 + 2.0 * z_log_sigma - tf.square(z_mu) - tf.exp(2.0 * z_log_sigma), 1)) # Add l2 loss cost_vae = tf.reduce_mean(loss_x + loss_z) else: # Just optimize l2 loss cost_vae = tf.reduce_mean(loss_x) # Alexnet for clasification based on softmax using TensorFlow slim if softmax: axis = list(range(len(x.get_shape()))) mean1, variance1 = tf.nn.moments(t, axis) \ if (phase_train is True) else tf.nn.moments(x, axis) mean2, variance2 = tf.nn.moments(y, axis) var_prob = variance2 / variance1 # Input of the classification network current_input2 = utils.corrupt(x)*corrupt_cls + \ x*(1-corrupt_cls) \ if (denoising and phase_train is True) else x current_input2.set_shape(x.get_shape()) current_input2 = utils.to_tensor(current_input2) \ if convolutional else current_input2 y_concat = tf.concat([current_input2, y], 3) with tf.variable_scope('deconv/concat'): shape = shapes[layer_i + 1] if convolutional: # Here we set the input of classification network is # the twice of # the input of the reconstruction network # 112->224 for alexNet and 150->300 for inception v3 and v4 y_concat, W = utils.deconv2d( x=y_concat, n_output_h=y_concat.get_shape()[1] * 2, n_output_w=y_concat.get_shape()[1] * 2, n_output_ch=y_concat.get_shape()[3], n_input_ch=y_concat.get_shape()[3], k_h=3, k_w=3) Ws.append(W) # The following are optional networks for classification network if classifier == 'squeezenet': predictions, net = squeezenet.squeezenet(y_concat, num_classes=13) elif classifier == 'zigzagnet': predictions, net = squeezenet.zigzagnet(y_concat, num_classes=13) elif classifier == 'alexnet_v2': predictions, end_points = alexnet.alexnet_v2(y_concat, num_classes=13) elif classifier == 'inception_v1': predictions, end_points = inception.inception_v1(y_concat, num_classes=13) elif classifier == 'inception_v2': predictions, end_points = inception.inception_v2(y_concat, num_classes=13) elif classifier == 'inception_v3': predictions, end_points = inception.inception_v3(y_concat, num_classes=13) label_onehot = tf.one_hot(label, 13, axis=-1, dtype=tf.int32) cost_s = tf.losses.softmax_cross_entropy(label_onehot, predictions) cost_s = tf.reduce_mean(cost_s) acc = tf.nn.in_top_k(predictions, label, 1) else: predictions = tf.one_hot(label, 13, 1, 0) label_onehot = tf.one_hot(label, 13, 1, 0) cost_s = 0 acc = 0 # Using Summaries for Tensorboard tf.summary.scalar('cost_vae', cost_vae) tf.summary.scalar('cost_s', cost_s) tf.summary.scalar('loss_x', loss_x) tf.summary.scalar('loss_z', loss_z) tf.summary.scalar('corrupt_rec', corrupt_rec) tf.summary.scalar('corrupt_cls', corrupt_cls) tf.summary.scalar('var_prob', var_prob) merged = tf.summary.merge_all() return { 'cost_vae': cost_vae, 'cost_s': cost_s, 'loss_x': loss_x, 'loss_z': loss_z, 'Ws': Ws, 'x': x, 't': t, 'label': label, 'label_onehot': label_onehot, 'predictions': predictions, 'z': z, 'y': y, 'acc': acc, 'keep_prob': keep_prob, 'corrupt_rec': corrupt_rec, 'corrupt_cls': corrupt_cls, 'var_prob': var_prob, 'train': phase_train, 'merged': merged }
validation_iterator = validation_dataset.make_one_shot_iterator() # Create a feedable iterator that use a placeholder to switch between dataset handle = tf.placeholder(tf.string) iterator = tf.contrib.data.Iterator.from_string_handle( handle, train_iterator.output_types, train_iterator.output_shapes) image, pose_q, pose_x = iterator.get_next() #################################################################################################### # Construct model and encapsulating all ops into scopes, making # Tensorboard's Graph visualization more convenient with tf.name_scope('Model'): py_x, _ = inception.inception_v3(image) py_x = tf.nn.relu(py_x) weights = { 'h1': tf.Variable(tf.random_normal([1000, 4]), name='w_wpqr_out'), 'h2': tf.Variable(tf.random_normal([1000, 3]), name='w_xyz_out'), } biases = { 'b1': tf.Variable(tf.zeros([4]), name='b_wpqr_out'), 'b2': tf.Variable(tf.zeros([3]), name='b_xyz_out'), } cls3_fc_pose_wpqr = tf.add(tf.matmul(py_x, weights['h1']), biases['b1']) cls3_fc_pose_xyz = tf.add(tf.matmul(py_x, weights['h2']), biases['b2'])
def main(argv): # TF Record dataset = tf.data.TFRecordDataset(FLAGS.data_dir + '/dataset_test.tfrecords') dataset = dataset.map(_parse_function_kingscollege) # dataset = dataset.repeat() # dataset = dataset.shuffle(FLAGS.queue_buffer) dataset = dataset.batch(1) image, vec, pose_q, pose_x = dataset.make_one_shot_iterator().get_next() # Network Definition image_resized = tf.image.resize_images(image, size=[224, 224]) if FLAGS.loss == 'PoseNet': y_pred, _ = inception.inception_v3(image_resized, num_classes=7, is_training=False) quaternion_pred, translation_pred = tf.split(y_pred, [4, 3], axis=1) sess = tf.Session() ckpt_file = tf.train.latest_checkpoint(FLAGS.model_dir) tf.train.Saver().restore(sess, ckpt_file) print('restoring parameters from', ckpt_file) i = 0 results = [] try: while True: _image, _quaternion_true, _translation_true, _quaternion_pred, _translation_pred = \ sess.run([image, pose_q, pose_x, quaternion_pred, translation_pred]) # Compute Individual Sample Error q1 = _quaternion_true / np.linalg.norm(_quaternion_true) q2 = _quaternion_pred / np.linalg.norm(_quaternion_pred) d = abs(np.sum(np.multiply(q1, q2))) theta = 2. * np.arccos(d) * 180. / np.pi error_x = np.linalg.norm(_translation_true - _translation_pred) results.append([error_x, theta]) print('Iteration:', i, 'Error XYZ (m):', error_x, 'Error Q (degrees):', theta) i = i + 1 except tf.errors.OutOfRangeError: print('End of Test Data') results = np.stack(results) results = np.median(results, axis=0) print('Error XYZ (m):', results[0], 'Error Q (degrees):', results[1]) elif FLAGS.loss == 'SE3': y_pred, _ = inception.inception_v3(image_resized, num_classes=6, is_training=False) sess = tf.Session() ckpt_file = tf.train.latest_checkpoint(FLAGS.model_dir) tf.train.Saver().restore(sess, ckpt_file) print('restoring parameters from', ckpt_file) SO3_GROUP = SpecialOrthogonalGroup(3) SE3_GROUP = SpecialEuclideanGroup(3) metric = InvariantMetric(group=SE3_GROUP, inner_product_mat_at_identity=np.eye(6), left_or_right='left') i = 0 results = [] _y_pred_i = [] _y_true_i = [] _se3_err_i = [] try: while True: _image, _rvec, _qvec, _tvec, _y_pred = \ sess.run([image, vec, pose_q, pose_x, y_pred]) _quaternion_true = _qvec _quaternion_pred = SO3_GROUP.quaternion_from_rotation_vector( _y_pred[0, :3])[0] # Compute Individual Sample Error q1 = _quaternion_true / np.linalg.norm(_quaternion_true) q2 = _quaternion_pred / np.linalg.norm(_quaternion_pred) d = abs(np.sum(np.multiply(q1, q2))) theta = 2. * np.arccos(d) * 180. / np.pi error_x = np.linalg.norm(_tvec - _y_pred[0, 3:]) results.append([error_x, theta]) # SE3 compute _y_true = np.concatenate((_rvec, _tvec), axis=-1) se3_dist = metric.squared_dist(_y_pred, _y_true)[0] _y_pred_i.append(_y_pred) _y_true_i.append(_y_true) _se3_err_i.append( SE3_GROUP.compose(SE3_GROUP.inverse(_y_true), _y_pred)) print('Iteration:', i, 'Error XYZ (m):', error_x, 'Error Q (degrees):', theta, 'SE3 dist:', se3_dist) i = i + 1 except tf.errors.OutOfRangeError: print('End of Test Data') # Calculate SE3 Error Weights err_vec = np.vstack(_se3_err_i) err_weights = np.diag(np.linalg.inv(np.cov(err_vec.T))) err_weights = err_weights / np.linalg.norm(err_weights) print(err_weights) results = np.stack(results) results = np.median(results, axis=0) print('Error XYZ (m):', results[0], 'Error Q (degrees):', results[1]) else: print('Invalid Option:', FLAGS.loss) raise SystemExit
# Variables W1 = tf.Variable(tf.Variable(tf.random_normal([2048, hidden_layer])),name="W1") b1 = tf.Variable(tf.Variable(tf.random_normal([hidden_layer])),name='b1') W2 = tf.Variable(tf.Variable(tf.random_normal([hidden_layer,hidden_layer2])),name="W2") b2 = tf.Variable(tf.Variable(tf.random_normal([hidden_layer2])),name='b2') W3 = tf.Variable(tf.Variable(tf.random_normal([hidden_layer2,1])),name="W3") b3 = tf.Variable(tf.Variable(tf.random_normal([1])),name='b3') #pdb.set_trace() slim = tf.contrib.slim # Inception model with slim.arg_scope(inception.inception_v3_arg_scope()): _, end_points = inception.inception_v3(x, num_classes=1001, is_training=False) # Selecting top n number of frames output_feature = tf.squeeze(end_points['PreLogits'],[1,2]) #feature vector shape=(batch_size,num of frames,feature vector size) # bb = tf.split(output_feature, ind) bb = tf.split(input_feature, ind) out = [] for i in bb: aa = calculate_feature_score(i,W1,b1,W2,b2,W3,b3) #importance score shape=(batch_size,num of frames) sorted_a, indices = tf.nn.top_k(tf.transpose(aa), n_input) indices = tf.transpose(tf.transpose(indices)[::-1]) #shape_a = tf.shape(aa) #auxiliary_indices = tf.meshgrid(*[tf.range(d) for d in (tf.unstack(shape_a[:(aa.get_shape().ndims - 1)]) + [n_input])], indexing='ij') #sorted_b = tf.gather_nd(bb, tf.stack(auxiliary_indices[:-1] + [indices], axis=-1))# selected k number of important feature vector sorted_b = tf.gather(i,tf.squeeze(indices,0))[::-1]