Not getting bounding box for YOLO v3 model

I have implemented YOLO v3 model using this https://github.com/AntonMu/TrainYourOwnYOLO and trained the model and acquired a loss of 1.05, but during testing, although if I give a trained image to the model it is not able to predict the label and not able to draw bounding box on it .

so I started debugging and found the origin of the error :

 out_boxes, out_scores, out_classes = self.sess.run(
            [self.boxes, self.scores, self.classes],
            feed_dict={
                self.yolo_model.input: image_data,
                self.input_image_shape: [image.size[1], image.size[0]],
                K.learning_phase(): 0
            },
        )

 print("out_boxes",out_boxes)      #prints [ ]
 print("out_classes",out_classes)  # prints [ ]
 print("out_scores",out_scores)    # prints [ ]

where:

self.boxes= Tensor("concat_11:0", shape=(?, 4), dtype=float32)
self.scores=Tensor("concat_12:0", shape=(?,), dtype=float32)
self.classes=Tensor("concat_13:0", shape=(?,), dtype=int32)

I trained the YOLO v3 model on 168 classes, each class having 36 images.

can someone help?? is there an issue with self.boxes/self.scores/self.classes ?? if there is no issue with them what's the issue with self.sess.run ??