dgcnn_evaluate.py

# Modified evaluation script of PointNet for DGCNN
# (unofficial)

import argparse
import math
import h5py
import numpy as np
import tensorflow as tf
import socket
import importlib
import os
import sys
BASE_DIR = os.path.dirname(os.path.abspath(__file__))
sys.path.append(BASE_DIR)
sys.path.append(os.path.join(BASE_DIR, 'models'))
sys.path.append(os.path.join(BASE_DIR, 'utils'))
import provider
import tf_util




parser = argparse.ArgumentParser()
parser.add_argument('--gpu', type=int, default=0, help='GPU to use [default: GPU 0]')
parser.add_argument('--model', default='dgcnn', help='Model name: dgcnn')
parser.add_argument('--log_dir', default='log', help='Log dir [default: log]')
parser.add_argument('--num_point', type=int, default=1024, help='Point Number [256/512/1024/2048] [default: 1024]')
parser.add_argument('--max_epoch', type=int, default=250, help='Epoch to run [default: 250]')
parser.add_argument('--batch_size', type=int, default=24, help='Batch Size during training [default: 32]')
parser.add_argument('--learning_rate', type=float, default=0.001, help='Initial learning rate [default: 0.001]')
parser.add_argument('--momentum', type=float, default=0.9, help='Initial learning rate [default: 0.9]')
parser.add_argument('--optimizer', default='adam', help='adam or momentum [default: adam]')
parser.add_argument('--decay_step', type=int, default=200000, help='Decay step for lr decay [default: 200000]')
parser.add_argument('--decay_rate', type=float, default=0.7, help='Decay rate for lr decay [default: 0.8]')
parser.add_argument('--dump_dir', default='dump', help='dump folder path [dump]')
parser.add_argument('--model_path', default='log/model.ckpt', help='model checkpoint file path [default: log/model.ckpt]')

FLAGS = parser.parse_args()



BATCH_SIZE = FLAGS.batch_size
NUM_POINT = FLAGS.num_point
MAX_EPOCH = FLAGS.max_epoch
BASE_LEARNING_RATE = FLAGS.learning_rate
GPU_INDEX = FLAGS.gpu
MOMENTUM = FLAGS.momentum
OPTIMIZER = FLAGS.optimizer
DECAY_STEP = FLAGS.decay_step
DECAY_RATE = FLAGS.decay_rate
DUMP_DIR = FLAGS.dump_dir
MODEL_PATH = FLAGS.model_path

MODEL = importlib.import_module(FLAGS.model) # import network module
MODEL_FILE = os.path.join(BASE_DIR, 'models', FLAGS.model+'.py')
LOG_DIR = FLAGS.log_dir
if not os.path.exists(LOG_DIR): os.mkdir(LOG_DIR)
os.system('cp %s %s' % (MODEL_FILE, LOG_DIR)) # bkp of model def
os.system('cp train.py %s' % (LOG_DIR)) # bkp of train procedure
LOG_FOUT = open(os.path.join(LOG_DIR, 'log_train.txt'), 'w')
LOG_FOUT.write(str(FLAGS)+'\n')

MAX_NUM_POINT = 2048
NUM_CLASSES = 40

BN_INIT_DECAY = 0.5
BN_DECAY_DECAY_RATE = 0.5
BN_DECAY_DECAY_STEP = float(DECAY_STEP)
BN_DECAY_CLIP = 0.99

HOSTNAME = socket.gethostname()

# ModelNet40 official train/test split
TRAIN_FILES = provider.getDataFiles( \
    os.path.join(BASE_DIR, 'data/modelnet40_ply_hdf5_2048/train_files.txt'))
TEST_FILES = provider.getDataFiles(\
    os.path.join(BASE_DIR, 'data/modelnet40_ply_hdf5_2048/test_files.txt'))
SHAPE_NAMES = [line.rstrip() for line in \
    open(os.path.join(BASE_DIR, 'data/modelnet40_ply_hdf5_2048/shape_names.txt'))] 
    
def log_string(out_str):
    LOG_FOUT.write(out_str+'\n')
    LOG_FOUT.flush()
    print(out_str)

def get_learning_rate(batch):
    learning_rate = tf.train.exponential_decay(
                        BASE_LEARNING_RATE,  # Base learning rate.
                        batch * BATCH_SIZE,  # Current index into the dataset.
                        DECAY_STEP,          # Decay step.
                        DECAY_RATE,          # Decay rate.
                        staircase=True)
    learning_rate = tf.maximum(learning_rate, 0.00001) # CLIP THE LEARNING RATE!
    return learning_rate        

def get_bn_decay(batch):
    bn_momentum = tf.train.exponential_decay(
                      BN_INIT_DECAY,
                      batch*BATCH_SIZE,
                      BN_DECAY_DECAY_STEP,
                      BN_DECAY_DECAY_RATE,
                      staircase=True)
    bn_decay = tf.minimum(BN_DECAY_CLIP, 1 - bn_momentum)
    return bn_decay

def evaluate(num_votes):
    is_training = False
     
    with tf.device('/gpu:'+str(GPU_INDEX)):
        pointclouds_pl, labels_pl = MODEL.placeholder_inputs(BATCH_SIZE, NUM_POINT)
        is_training_pl = tf.placeholder(tf.bool, shape=())
        print(is_training_pl)
        
        # Note the global_step=batch parameter to minimize. 
        # That tells the optimizer to helpfully increment the 'batch' parameter for you every time it trains.
        batch = tf.Variable(0)
        bn_decay = get_bn_decay(batch)
        tf.summary.scalar('bn_decay', bn_decay)

        # Get model and loss 
        pred, end_points = MODEL.get_model(pointclouds_pl, is_training_pl, bn_decay=bn_decay)
        loss = MODEL.get_loss(pred, labels_pl, end_points)
        tf.summary.scalar('loss', loss)

        correct = tf.equal(tf.argmax(pred, 1), tf.to_int64(labels_pl))
        accuracy = tf.reduce_sum(tf.cast(correct, tf.float32)) / float(BATCH_SIZE)
        tf.summary.scalar('accuracy', accuracy)

        # Get training operator
        learning_rate = get_learning_rate(batch)
        tf.summary.scalar('learning_rate', learning_rate)
        if OPTIMIZER == 'momentum':
            optimizer = tf.train.MomentumOptimizer(learning_rate, momentum=MOMENTUM)
        elif OPTIMIZER == 'adam':
            optimizer = tf.train.AdamOptimizer(learning_rate)
        train_op = optimizer.minimize(loss, global_step=batch)
        
        # Add ops to save and restore all the variables.
        saver = tf.train.Saver()
        
    # Create a session
    config = tf.ConfigProto()
    config.gpu_options.allow_growth = True
    config.allow_soft_placement = True
    config.log_device_placement = False
    sess = tf.Session(config=config)

    # Restore variables from disk.
    saver.restore(sess, MODEL_PATH)
    log_string("Model restored.")

    # Add summary writers
    #merged = tf.merge_all_summaries()
    merged = tf.summary.merge_all()

    ops = {'pointclouds_pl': pointclouds_pl,
           'labels_pl': labels_pl,
           'is_training_pl': is_training_pl,
           'pred': pred,
           'loss': loss,
           'train_op': train_op,
           'merged': merged,
           'step': batch}

    eval_one_epoch(sess, ops, num_votes)

   
def eval_one_epoch(sess, ops, num_votes=1, topk=1):
    error_cnt = 0
    is_training = False
    total_correct = 0
    total_seen = 0
    loss_sum = 0
    total_seen_class = [0 for _ in range(NUM_CLASSES)]
    total_correct_class = [0 for _ in range(NUM_CLASSES)]
    for fn in range(len(TEST_FILES)):
        log_string('----'+str(fn)+'----')
        current_data, current_label = provider.loadDataFile(TEST_FILES[fn])
        current_data = current_data[:,0:NUM_POINT,:]
        current_label = np.squeeze(current_label)
        print(current_data.shape)
        
        file_size = current_data.shape[0]
        num_batches = file_size // BATCH_SIZE
        print(file_size)
        
        for batch_idx in range(num_batches):
            start_idx = batch_idx * BATCH_SIZE
            end_idx = (batch_idx+1) * BATCH_SIZE
            cur_batch_size = end_idx - start_idx
            
            # Aggregating BEG
            batch_loss_sum = 0 # sum of losses for the batch
            batch_pred_sum = np.zeros((cur_batch_size, NUM_CLASSES)) # score for classes
            batch_pred_classes = np.zeros((cur_batch_size, NUM_CLASSES)) # 0/1 for classes
            for vote_idx in range(num_votes):
                orig_data = current_data[start_idx:end_idx, :, :]
                rotated_data = provider.rotate_point_cloud_by_angle(orig_data,
                                                  vote_idx/float(num_votes) * np.pi * 2)
                feed_dict = {ops['pointclouds_pl']: rotated_data, #orig_data or rotated_data
                             ops['labels_pl']: current_label[start_idx:end_idx],
                             ops['is_training_pl']: is_training}
                loss_val, pred_val = sess.run([ops['loss'], ops['pred']],
                                          feed_dict=feed_dict)
                batch_pred_sum += pred_val
                batch_pred_val = np.argmax(pred_val, 1)
                for el_idx in range(cur_batch_size):
                    batch_pred_classes[el_idx, batch_pred_val[el_idx]] += 1
                batch_loss_sum += (loss_val * cur_batch_size / float(num_votes))
            # pred_val_topk = np.argsort(batch_pred_sum, axis=-1)[:,-1*np.array(range(topk))-1]
            # pred_val = np.argmax(batch_pred_classes, 1)
            pred_val = np.argmax(batch_pred_sum, 1)
            # Aggregating END
            
            correct = np.sum(pred_val == current_label[start_idx:end_idx])




            # correct = np.sum(pred_val_topk[:,0:topk] == label_val)
            total_correct += correct
            total_seen += cur_batch_size
            loss_sum += batch_loss_sum

            for i in range(start_idx, end_idx):
                l = current_label[i]
                total_seen_class[l] += 1
                total_correct_class[l] += (pred_val[i-start_idx] == l)
                
          
                
    log_string('eval mean loss: %f' % (loss_sum / float(total_seen)))
    log_string('eval accuracy: %f' % (total_correct / float(total_seen)))
    log_string('eval avg class acc: %f' % (np.mean(np.array(total_correct_class)/np.array(total_seen_class,dtype=np.float))))
    
    class_accuracies = np.array(total_correct_class)/np.array(total_seen_class,dtype=np.float)
    for i, name in enumerate(SHAPE_NAMES):
        log_string('%10s:\t%0.3f' % (name, class_accuracies[i]))
    
    

if __name__=='__main__':
    with tf.Graph().as_default():
        evaluate(num_votes=1)
    LOG_FOUT.close()