help!help!help!Test run failed

[PanJinquan]

I download your Github code and the corresponding model file：https://github.com/Joker316701882/Deep-Image-Matting，Then run：python test.py --alpha=./test_data/alpha/1.png --rgb=./test_data/RGB/1.png，But error in this procedure：saver.restore(sess,tf.train.latest_checkpoint('./model'))#PS：I have downloaded your model and put it in the "model" file. Here errors：InvalidArgumentError (see above for traceback): No OpKernel was registered to support Op 'MaxPoolWithArgmax' with these attrs. Registered devices: [CPU], Registered kernels:

[[Node: pool1 = MaxPoolWithArgmaxT=DT_FLOAT, Targmax=DT_INT64, ksize=[1, 2, 2, 1], padding="SAME", strides=[1, 2, 2, 1]]]

[fpipart]

This function 'MaxPoolWithArgmax' runs only on GPU on older version of tensorflow: https://github.com/tensorflow/tensorflow/issues/6035

It should work on CPU with tensorflow 1.8

[elzeru]

Just tried 1.8 CPU, works like a charm, and the upgrade is very easy to do. On my Debian: pip3 install --upgrade tensorflow

[shliang0603]

@PanJinquan Can you send me the pretrained model, I can't download it ,my email is :[email protected] Thanks

[shliang0603]

@PanJinquan 哥哥，你有Deep-Image-Matting的数据集吗，可以发我一份吗，谢谢啦 ，我的email: [email protected]

[chenhaocs]

I download your Github code and the corresponding model file：https://github.com/Joker316701882/Deep-Image-Matting，Then run：python test.py --alpha=./test_data/alpha/1.png --rgb=./test_data/RGB/1.png，But error in this procedure：saver.restore(sess,tf.train.latest_checkpoint('./model'))#PS：I have downloaded your model and put it in the "model" file. Here errors：InvalidArgumentError (see above for traceback): No OpKernel was registered to support Op 'MaxPoolWithArgmax' with these attrs. Registered devices: [CPU], Registered kernels: [[Node: pool1 = MaxPoolWithArgmaxT=DT_FLOAT, Targmax=DT_INT64, ksize=[1, 2, 2, 1], padding="SAME", strides=[1, 2, 2, 1]]]

@PanJinquan Hello, could you send me your pre-trained model and the training datasets? Thanks a lot! My email [email protected]

[rainsun1]

@PanJinquan could you ALSO send me your pre-trained model and the training datasets? Thanks! email: [email protected]

[ssxlconch]

I download your Github code and the corresponding model file：https://github.com/Joker316701882/Deep-Image-Matting，Then run：python test.py --alpha=./test_data/alpha/1.png --rgb=./test_data/RGB/1.png，But error in this procedure：saver.restore(sess,tf.train.latest_checkpoint('./model'))#PS：I have downloaded your model and put it in the "model" file. Here errors：InvalidArgumentError (see above for traceback): No OpKernel was registered to support Op 'MaxPoolWithArgmax' with these attrs. Registered devices: [CPU], Registered kernels: [[Node: pool1 = MaxPoolWithArgmaxT=DT_FLOAT, Targmax=DT_INT64, ksize=[1, 2, 2, 1], padding="SAME", strides=[1, 2, 2, 1]]]

sorry for bothering, would you please send me the pretrained-model? my emai: [email protected]