使用mobilenet进行训练

[junedgar]

感谢您的分享！能否请教您点问题。 使用mobilenetv2进行训练的时候，报错如下： train() File "train.py", line 47, in train gtboxes_batch=gtboxes_and_label) File "../libs/networks/build_whole_network.py", line 211, in build_whole_detection_network feature_stride8, feature_stride16 = self.build_base_network(input_img_batch) File "/home/startdt/zhengjunjun/zhengpy27/local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 439, in __iter__ "Tensor objects are not iterable when eager execution is not " TypeError: Tensor objects are not iterable when eager execution is not enabled. To iterate over this tensor use tf.map_fn. 发现相对于使用resnet训练，返回的是C3,C4两个特征图，https://github.com/DetectionTeamUCAS/SSH_Tensorflow/blob/590105b42575953b76d5b02a1a3040c57a0a5069/libs/networks/resnet.py#L122 mobilenet base_network只返回一张特征图，https://github.com/DetectionTeamUCAS/SSH_Tensorflow/blob/590105b42575953b76d5b02a1a3040c57a0a5069/libs/networks/mobilenet_v2.py#L111 请问我该如何修改？ @yangxue0827