You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
新手,调试了一下午,跟着教程走的,先是遇到In PaddlePaddle 2.x, we turn on dynamic graph mode by default, and 'data()' is only supported in static graph mode. So if you want to use this api, please call 'paddle.enable_static()' before this api to enter static graph mode.解决之后又出现维度的问题,product = paddle.add(x=product, y=attn_bias)在这里, Broadcast dimension mismatch. Operands could not be broadcast together with the shape of X = [5, 12, 1, 1] and the shape of Y = [5, 12, 5]. Received [12] in X is not equal to [5] in Y at i:1.reshape之后又lstm_forward_fc = static.nn.fc(x=video_input_tensor,
size=self.lstm_size_img * 4,
activation=None,
bias_attr=False) 出现The input tensor X's dimensions of MulOp should be larger than x_num_col_dims. But received X's dimensions = 1, X's shape = [2048], x_num_col_dims = 1.请问是哪里的问题,该如何解决呢
The text was updated successfully, but these errors were encountered:
新手,调试了一下午,跟着教程走的,先是遇到In PaddlePaddle 2.x, we turn on dynamic graph mode by default, and 'data()' is only supported in static graph mode. So if you want to use this api, please call 'paddle.enable_static()' before this api to enter static graph mode.解决之后又出现维度的问题,product = paddle.add(x=product, y=attn_bias)在这里, Broadcast dimension mismatch. Operands could not be broadcast together with the shape of X = [5, 12, 1, 1] and the shape of Y = [5, 12, 5]. Received [12] in X is not equal to [5] in Y at i:1.reshape之后又lstm_forward_fc = static.nn.fc(x=video_input_tensor,
size=self.lstm_size_img * 4,
activation=None,
bias_attr=False) 出现The input tensor X's dimensions of MulOp should be larger than x_num_col_dims. But received X's dimensions = 1, X's shape = [2048], x_num_col_dims = 1.请问是哪里的问题,该如何解决呢
The text was updated successfully, but these errors were encountered: