fixed indent and import issue

@@ -10,6 +10,7 @@ from data_utils import get_batch_data
 from misc_utils import parse_anchors, read_class_names, AverageMeter
 from misc_utils import parse_anchors, read_class_names, AverageMeter
 from eval_utils import evaluate_on_cpu, evaluate_on_gpu, get_preds_gpu, voc_eval, parse_gt_rec
 from eval_utils import evaluate_on_cpu, evaluate_on_gpu, get_preds_gpu, voc_eval, parse_gt_rec
 from nms_utils import gpu_nms
 from nms_utils import gpu_nms
+from tfrecord_utils import TFRecordIterator
 
 
 from model import yolov3
 from model import yolov3
 
 

@@ -57,7 +57,7 @@ for y in y_true:
 
 
 
 
 ### Model definition
 ### Model definition
-yolo_model = yolov3(class_num, anchors, use_label_smooth, use_focal_loss, batch_norm_decay, weight_decay, use_static_shape=False)
+yolo_model = yolov3(args.class_num, args.anchors, args.use_label_smooth, args.use_focal_loss, args.batch_norm_decay, args.weight_decay, use_static_shape=False)
 
 
 with tf.variable_scope('yolov3'):
 with tf.variable_scope('yolov3'):
     pred_feature_maps = yolo_model.forward(image, is_training=is_training)
     pred_feature_maps = yolo_model.forward(image, is_training=is_training)
@@ -67,14 +67,14 @@ y_pred = yolo_model.predict(pred_feature_maps)
 
 
 l2_loss = tf.losses.get_regularization_loss()
 l2_loss = tf.losses.get_regularization_loss()
 
 
-saver_to_restore = tf.train.Saver(var_list=tf.contrib.framework.get_variables_to_restore(include=restore_include, exclude=restore_exclude))
-update_vars = tf.contrib.framework.get_variables_to_restore(include=update_part)
+saver_to_restore = tf.train.Saver(var_list=tf.contrib.framework.get_variables_to_restore(include=args.restore_include, exclude=args.restore_exclude))
+update_vars = tf.contrib.framework.get_variables_to_restore(include=args.update_part)
 
 
 
 
 global_step = tf.Variable(float(args.global_step), trainable=False, collections=[tf.GraphKeys.LOCAL_VARIABLES])
 global_step = tf.Variable(float(args.global_step), trainable=False, collections=[tf.GraphKeys.LOCAL_VARIABLES])
-if use_warm_up:
-    learning_rate = tf.cond(tf.less(global_step, train_batch_num * warm_up_epoch), 
-                            lambda: learning_rate_init * global_step / (train_batch_num * warm_up_epoch),
+if args.use_warm_up:
+    learning_rate = tf.cond(tf.less(global_step, args.train_batch_num * args.warm_up_epoch), 
+                            lambda: args.learning_rate_init * args.global_step / (args.train_batch_num * args.warm_up_epoch),
                             lambda: config_learning_rate(args, global_step - args.train_batch_num * args.warm_up_epoch))
                             lambda: config_learning_rate(args, global_step - args.train_batch_num * args.warm_up_epoch))
 else:
 else:
     learning_rate = config_learning_rate(args, global_step)
     learning_rate = config_learning_rate(args, global_step)
@@ -196,7 +196,7 @@ with tf.Session() as sess:
 
 
         val_preds = []
         val_preds = []
 
 
-      for j in trange(val_img_cnt):
+        for j in trange(args.val_img_cnt):
             __image_ids, __y_pred, __loss = sess.run([image_ids, y_pred, loss],
             __image_ids, __y_pred, __loss = sess.run([image_ids, y_pred, loss],
                                                     feed_dict={is_training: False})
                                                     feed_dict={is_training: False})
             pred_content = get_preds_gpu(sess, gpu_nms_op, pred_boxes_flag, pred_scores_flag, __image_ids, __y_pred)
             pred_content = get_preds_gpu(sess, gpu_nms_op, pred_boxes_flag, pred_scores_flag, __image_ids, __y_pred)
@@ -209,12 +209,12 @@ with tf.Session() as sess:
 
 
         # calc mAP
         # calc mAP
         rec_total, prec_total, ap_total = AverageMeter(), AverageMeter(), AverageMeter()
         rec_total, prec_total, ap_total = AverageMeter(), AverageMeter(), AverageMeter()
-      gt_dict = parse_gt_rec(val_file, 'GZIP', img_size, letterbox_resize)
+        gt_dict = parse_gt_rec(args.val_file, 'GZIP', args.img_size, args.letterbox_resize)
 
 
         info = '======> Epoch: {}, global_step: {}, lr: {:.6g} <======\n'.format(epoch, __global_step, __lr)
         info = '======> Epoch: {}, global_step: {}, lr: {:.6g} <======\n'.format(epoch, __global_step, __lr)
 
 
-      for ii in range(class_num):
-          npos, nd, rec, prec, ap = voc_eval(gt_dict, val_preds, ii, iou_thres=eval_threshold, use_07_metric=use_voc_07_metric)
+        for ii in range(args.class_num):
+            npos, nd, rec, prec, ap = voc_eval(gt_dict, val_preds, ii, iou_thres=args.eval_threshold, use_07_metric=args.use_voc_07_metric)
             info += 'EVAL: Class {}: Recall: {:.4f}, Precision: {:.4f}, AP: {:.4f}\n'.format(ii, rec, prec, ap)
             info += 'EVAL: Class {}: Recall: {:.4f}, Precision: {:.4f}, AP: {:.4f}\n'.format(ii, rec, prec, ap)
             rec_total.update(rec, npos)
             rec_total.update(rec, npos)
             prec_total.update(prec, nd)
             prec_total.update(prec, nd)
@@ -226,7 +226,7 @@ with tf.Session() as sess:
             val_loss_total.average, val_loss_xy.average, val_loss_wh.average, val_loss_conf.average, val_loss_class.average)
             val_loss_total.average, val_loss_xy.average, val_loss_wh.average, val_loss_conf.average, val_loss_class.average)
         print(info)
         print(info)
 
 
-      if save_optimizer and mAP > best_mAP:
+        if args.save_optimizer and mAP > best_mAP:
             best_mAP = mAP
             best_mAP = mAP
-          saver_best.save(sess, save_dir + 'best_model_Epoch_{}_step_{}_mAP_{:.4f}_loss_{:.4f}_lr_{:.7g}'.format(
+            saver_best.save(sess, args.save_dir + 'best_model_Epoch_{}_step_{}_mAP_{:.4f}_loss_{:.4f}_lr_{:.7g}'.format(
                                 epoch, int(__global_step), best_mAP, val_loss_total.average, __lr))
                                 epoch, int(__global_step), best_mAP, val_loss_total.average, __lr))
\ No newline at end of file