search

GuangmingZhu / Conv3D_CLSTM

Multimodal Gesture Recognition Using 3D Convolution and Convolutional LSTM
90 stars 35 forks source link

TypeError: __init__() missing 1 required positional argument: 'prev_layer' #13

Open peach2wanzi opened 5 years ago

peach2wanzi commented 5 years ago

I have replaced RNNLayer code with the tensorlayer-rnnlayer.py.But now it have a new problem.

I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: FMA [TL] WARNING: Function: tensorlayer.layers.utils.set_name_reuse (in file: /home/fang/3Dgesture/tensorlayer/layers/utils.py) is deprecated and will be removed after 2018-06-30. Instructions for updating: TensorLayer relies on TensorFlow to check name reusing

[TL] WARNING: this method is DEPRECATED and has no effect, please remove it from your code. [TL] WARNING: DeprecationWarning: BatchNormLayer.init(): layer argument is deprecated and will be removed in version 1.9, please change for prev_layer. [TL] WARNING: DeprecationWarning: BatchNormLayer.init(): layer argument is deprecated and will be removed in version 1.9, please change for prev_layer. [TL] WARNING: DeprecationWarning: BatchNormLayer.init(): layer argument is deprecated and will be removed in version 1.9, please change for prev_layer. Traceback (most recent call last): File "training_skig_rgb.py", line 49, in networks = net.c3d_clstm(x, num_classes, False, True) File "/home/fang/3Dgesture/c3d_clstm.py", line 86, in c3d_clstm name='clstm_layer_1') File "/home/fang/3Dgesture/tensorlayer/layers/recurrent.py", line 55, in init Layer.init(self, name=name) File "/home/fang/3Dgesture/tensorlayer/decorators/deprecated_alias.py", line 24, in wrapper return f(*args, **kwargs) TypeError: init() missing 1 required positional argument: 'prev_layer'

I erally don't know where is the point.....

peach2wanzi commented 5 years ago

@GuangmingZhu Thank you!!!

GuangmingZhu commented 5 years ago

@peach2wanzi This work is done with the old version of Tensorlayer. You can refer to the new network using keras in TF-1.2: https://github.com/GuangmingZhu/ContinuousGR and https://github.com/GuangmingZhu/AttentioninConvLSTM.