saver.restore fails

[xiaoxinyi]

Tensor name 

"incept3c/in3_conv5x5_19/batch_norm/cond/incept3c/in3_conv5x5_19/batch_norm/moments/momen

ts_1/mean/ExponentialMovingAverage/local_step" not found in checkpoint files /root/dl-

data/tutorial/yobiface/model/model-20160506.ckpt-500000

[JIEMIN1995]

@xiaoxinyi I also met the same question. Have you found the solution?

[Hitiron]

DataLossError (see above for traceback): Unable to open table file ../model: Failed precondition: ../model: perhaps your file is in a different file format and you need to use a different restore operator? [[Node: save/RestoreV2_1 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"](_arg_save/Const_0_0, save/RestoreV2_1/tensor_names, save/RestoreV2_1/shape_and_slices)]]

saver.restore fail

[MengWangTHU]

我不知道中文是不是可以哈，这个是模型问题，想办法下下来最新的model，包含完整的data文件和meta文件，通过meta文件就可以restore了。但是我restore之后出现了别的新问题，我完全无法解释了。

[Fannjh]

@MengWangTHU 你好，请问你是如何解决恢复模型出错的？能分享一下吗

[MengWangTHU]

你是说在facenet里面吗？我最近没有在用那个网络了，不过我之前确实运行成功了。

发自我的 iPhone

在 2018年1月28日，10:24，Fan Mr notifications@github.com 写道：

@MengWangTHU 你好，请问你是如何解决恢复模型出错的？能分享一下吗

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or mute the thread.

[yobibyte]

Sorry for late reply, I fixed the issue, you need to download the new model though.

[sonfire186]

Computed output size would be negative: -1 [input_size: 1, effective_filter_size: 3, stride: 1]
     [[{{node InceptionResnetV1/Logits/AvgPool_1a_8x8/AvgPool}}]]