ferry

您好，您上一个项目的File "C:\ProgramFilesMyself\Anaconda3\envs\garbage2\lib\site-packages\tensorflow\python\client\session.py", line 1095, in _run 'Cannot interpret feed_dict key as Tensor: ' + e.args[0]) TypeError: Cannot interpret feed_dict key as Tensor: Tensor Tensor("input_1:0", shape=(?, 456, 456, 3), dtype=float32) is...

关于准确度和loss值

2

总共10类，每类几百张照片，val accuracy 在第三轮就达到了1.0，之后一直不变。test accuracy 在前几轮不断上升，上升到第8轮为0.69，之后不断震荡、下降，50轮时，test accuracy 为0.3。loss下降缓慢，到第10轮之后下降的特别特别慢，几乎保持不变。请问楼主，这是什么原因。

关于mean_std.py

1

请问楼主大神，mean_std.py最后执行的结果也没有保存，那它对最后识别的准确率有什么影响，没看懂mean_std.py是干什么的，望您解答，谢谢您！

我也存在这样的问题，请问你解决了吗

2

我也存在这样的问题，请问你解决了吗 _Originally posted by @LwXxz in https://github.com/wusaifei/garbage_classify/issues/32#issuecomment-626302894_

Tensor Tensor("input_1:0", shape=(?, 456, 456, 3), dtype=float32) is not an element of this graph.

3

'Cannot interpret feed_dict key as Tensor: ' + e.args[0]) TypeError: Cannot interpret feed_dict key as Tensor: Tensor Tensor("input_1:0", shape=(?, 456, 456, 3), dtype=float32) is not an element of this graph....

关于.h5文件

1

您好，在代码中有很多,h5文件，是所有的.h5文件都要下载吗？谢谢您 还有这个地方怎么处理？需要下载吗。谢谢您 BASE_WEIGHTS_PATH = ( 'https://github.com/Callidior/keras-applications/' 'releases/download/efficientnet/') WEIGHTS_HASHES = { 'efficientnet-b0': ('163292582f1c6eaca8e7dc7b51b01c61' '5b0dbc0039699b4dcd0b975cc21533dc', 'c1421ad80a9fc67c2cc4000f666aa507' '89ce39eedb4e06d531b0c593890ccff3'), 'efficientnet-b1': ('d0a71ddf51ef7a0ca425bab32b7fa7f1' '6043ee598ecee73fc674d9560c8f09b0', '75de265d03ac52fa74f2f510455ba64f' '9c7c5fd96dc923cd4bfefa3d680c4b68'), 'efficientnet-b2': ('bb5451507a6418a574534aa76a91b106' 'f6b605f3b5dde0b21055694319853086', '433b60584fafba1ea3de07443b74cfd3' '2ce004a012020b07ef69e22ba8669333'),