验证已经训练模型报错（conda Mac cv2）

技术问答
1

I tensorflow/core/platform/CPU_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 AVX512F FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2020-08-28 13:17:34.799975: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f91bcf85d90 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2020-08-28 13:17:34.800005: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version
WARNING:tensorflow:Skipping loading of weights for layer conv2d_4 due to mismatch in number of weights (1 vs 2).
WARNING:tensorflow:Skipping loading of weights for layer conv2d_transpose_1 due to mismatch in number of weights (2 vs 1).

1 Like
2

看一下这篇文章的内容讲解是否可以解决你的问题？

4

这样只是屏蔽了tensorflow 环境报错，并没有解决这个警告
(TF2) hongshengdeMacBook-Pro:DifferentiableBinarization_TF2 whs$ python inference.py
WARNING:tensorflow:Skipping loading of weights for layer conv2d_4 due to mismatch in number of weights (1 vs 2).
WARNING:tensorflow:Skipping loading of weights for layer conv2d_transpose_1 due to mismatch in number of weights (2 vs 1).

5

不太确定 WARNING 这一类的输出是否是真的「出错」，
具体的有什么肉眼可见的错误吗？

cc @snowkylin @dpinthinker 来帮忙看一下？

6

解决了谢谢回复，原因是我在TF2环境中验证TF1训练的模型，入门新手请见谅

1 Like
7

赞，继续多多探索，持续分享哈。:+1: