momo1986
momo1986
Met the same problem in python 3.6
我因为设备限制，对话模型在colab上进行训练。想在小显存GPU上跑推断。 我只存了checkpoin文件和最优的结果文件，如图：  请问是否有demo可以加载该模型并进行中文对话呢？ 用默认对话的效果有些捉急：  感谢您。
Have same problem kiunet_org.
Looks like it needs to refer to correct boost_lib file and include file. I can find the boost_include file with "dpkg -S /usr/include/boost/" However, how can I find the correct...
> Building graph should be put out of camera capture loop: > > ```python > predictions = self.model(inputs, training_schedule) > pred_flow = predictions['flow'] > with tf.Session(config=config) as sess: > saver.restore(blablabla)...
> You should feed 2 placeholders to self.model(), instead of 2 constants. How can I give the 2 placeholders with the input and give it to the self.model and then...
I met similar problem: OS: Ubuntu 18.04 CUDA: 9.0 Python: 2.6 Tensorflow: 1.12 Head of Makefile's sceenshot:  Error: 
> [#28 (comment)](https://github.com/sampepose/flownet2-tf/issues/28#issuecomment-406941839) > > Edit: > You are using Python 2.6, seriously? Hi, Sorry. I am using Python 3.6 Refer to comment 28: Looks my issue has gone. Thanks...
Met the same problem, is there a document for fix of this problem?
> @momo1986 是不是因为OpenCV版本的问题，这个代码是基于OpenCV 3.2的。 报错在cv2.dilate函数上 另外，我threshold一路拿到0数组是什么原因，也没有看到起来的图片，是一块黑色的区域。但我又可以存frame作为图片