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)
@@ -190,43 +190,43 @@ with tf.Session() as sess:
                                    epoch, int(__global_step), best_mAP, val_loss_total.average, __lr))
                                    epoch, int(__global_step), best_mAP, val_loss_total.average, __lr))
                 
                 
       ## all epoches end
       ## all epoches end
-      sess.run(val_init_op)
-
-      val_loss_total, val_loss_xy, val_loss_wh, val_loss_conf, val_loss_class = AverageMeter(), AverageMeter(), AverageMeter(), AverageMeter(), AverageMeter()
-
-      val_preds = []
-
-      for j in trange(val_img_cnt):
-          __image_ids, __y_pred, __loss = sess.run([image_ids, y_pred, loss],
-                                                  feed_dict={is_training: False})
-          pred_content = get_preds_gpu(sess, gpu_nms_op, pred_boxes_flag, pred_scores_flag, __image_ids, __y_pred)
-          val_preds.extend(pred_content)
-          val_loss_total.update(__loss[0])
-          val_loss_xy.update(__loss[1])
-          val_loss_wh.update(__loss[2])
-          val_loss_conf.update(__loss[3])
-          val_loss_class.update(__loss[4])
-
-      # calc mAP
-      rec_total, prec_total, ap_total = AverageMeter(), AverageMeter(), AverageMeter()
-      gt_dict = parse_gt_rec(val_file, 'GZIP', img_size, letterbox_resize)
-
-      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)
-          info += 'EVAL: Class {}: Recall: {:.4f}, Precision: {:.4f}, AP: {:.4f}\n'.format(ii, rec, prec, ap)
-          rec_total.update(rec, npos)
-          prec_total.update(prec, nd)
-          ap_total.update(ap, 1)
-
-      mAP = ap_total.average
-      info += 'EVAL: Recall: {:.4f}, Precison: {:.4f}, mAP: {:.4f}\n'.format(rec_total.average, prec_total.average, mAP)
-      info += 'EVAL: loss: total: {:.2f}, xy: {:.2f}, wh: {:.2f}, conf: {:.2f}, class: {:.2f}\n'.format(
-          val_loss_total.average, val_loss_xy.average, val_loss_wh.average, val_loss_conf.average, val_loss_class.average)
-      print(info)
-
-      if save_optimizer and mAP > best_mAP:
-          best_mAP = mAP
-          saver_best.save(sess, save_dir + 'best_model_Epoch_{}_step_{}_mAP_{:.4f}_loss_{:.4f}_lr_{:.7g}'.format(
-                            epoch, int(__global_step), best_mAP, val_loss_total.average, __lr))
\ No newline at end of file
+        sess.run(val_init_op)
+
+        val_loss_total, val_loss_xy, val_loss_wh, val_loss_conf, val_loss_class = AverageMeter(), AverageMeter(), AverageMeter(), AverageMeter(), AverageMeter()
+
+        val_preds = []
+
+        for j in trange(args.val_img_cnt):
+            __image_ids, __y_pred, __loss = sess.run([image_ids, y_pred, loss],
+                                                    feed_dict={is_training: False})
+            pred_content = get_preds_gpu(sess, gpu_nms_op, pred_boxes_flag, pred_scores_flag, __image_ids, __y_pred)
+            val_preds.extend(pred_content)
+            val_loss_total.update(__loss[0])
+            val_loss_xy.update(__loss[1])
+            val_loss_wh.update(__loss[2])
+            val_loss_conf.update(__loss[3])
+            val_loss_class.update(__loss[4])
+
+        # calc mAP
+        rec_total, prec_total, ap_total = AverageMeter(), AverageMeter(), AverageMeter()
+        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)
+
+        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)
+            rec_total.update(rec, npos)
+            prec_total.update(prec, nd)
+            ap_total.update(ap, 1)
+
+        mAP = ap_total.average
+        info += 'EVAL: Recall: {:.4f}, Precison: {:.4f}, mAP: {:.4f}\n'.format(rec_total.average, prec_total.average, mAP)
+        info += 'EVAL: loss: total: {:.2f}, xy: {:.2f}, wh: {:.2f}, conf: {:.2f}, class: {:.2f}\n'.format(
+            val_loss_total.average, val_loss_xy.average, val_loss_wh.average, val_loss_conf.average, val_loss_class.average)
+        print(info)
+
+        if args.save_optimizer and mAP > best_mAP:
+            best_mAP = mAP
+            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))
\ No newline at end of file