fixed errors for evaluation

@@ -60,7 +60,7 @@ args = parser.parse_args()
 args.anchors = parse_anchors(args.anchor_path)
 args.classes = read_class_names(args.class_name_path)
 args.class_num = len(args.classes)
-args.img_cnt = len(open(args.eval_file, 'r').readlines())
+args.img_cnt = TFRecordIterator(args.eval_file, 'GZIP').count()
 
 # setting placeholders
 is_training = tf.placeholder(dtype=tf.bool, name="phase_train")

@@ -183,4 +183,48 @@ with tf.Session() as sess:
             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
+                                   epoch, int(__global_step), best_mAP, val_loss_total.average, __lr))
+                saver_to_restore.save(sess, restore_path)
+                
+      ## 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))
+          saver_to_restore.save(sess, restore_path)
\ No newline at end of file