I use "python setup.py install"download the fast-transformer mudule,came back to run the tran.py,it turns out....

[aefew45yhgwshbwe5r67iuj]

(pytorch2) E:\大创\video-bgm-generation-main>D:/Anaconda/envs/pytorch2/python.exe e:/大创/video-bgm-generation-main/src/train.py
name: debug
args Namespace(name='debug', lr=0.0001, batch_size=6, path=None, epochs=200, train_data='E:/大创/video-bgm-generation-main/dataset/lpd_5_prcem_mix_v8_10000.npz', gpus=None)
DEBUG MODE checkpoints will not be saved
num of encoder classes: [ 18 3 18 129 18 6 20 102 4865] [7, 1, 6]
D_MODEL 512 N_LAYER 12 N_HEAD 8 DECODER ATTN causal-linear

: [ 18 3 18 129 18 6 20 102 4865]
DEVICE COUNT: 1
VISIBLE: 0
n_parameters: 39,006,324
train_data: dataset
batch_size: 6
num_batch: 506
train_x: (3039, 9999, 9)
train_y: (3039, 9999, 9)
train_mask: (3039, 9999)
lr_init: 0.0001
DECAY_EPOCH: []
DECAY_RATIO: 0.1
Traceback (most recent call last):
File "e:\大创\video-bgm-generation-main\src\train.py", line 226, in
train_dp()
File "e:\大创\video-bgm-generation-main\src\train.py", line 169, in train_dp
losses = net(is_train=True, x=batch_x, target=batch_y, loss_mask=batch_mask, init_token=batch_init)
File "D:\Anaconda\envs\pytorch2\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "D:\Anaconda\envs\pytorch2\lib\site-packages\torch\nn\parallel\data_parallel.py", line 169, in forward
return self.module(*inputs[0], **kwargs[0])
File "D:\Anaconda\envs\pytorch2\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "e:\大创\video-bgm-generation-main\src\model.py", line 482, in forward
return self.train_forward(**kwargs)
File "e:\大创\video-bgm-generation-main\src\model.py", line 450, in train_forward
h, y_type = self.forward_hidden(x, memory=None, is_training=True, init_token=init_token)
File "e:\大创\video-bgm-generation-main\src\model.py", line 221, in forward_hidden
encoder_hidden = self.transformer_encoder(encoder_pos_emb, attn_mask)
File "D:\Anaconda\envs\pytorch2\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "D:\Anaconda\envs\pytorch2\lib\site-packages\pytorch_fast_transformers-0.4.0-py3.9-win-amd64.egg\fast_transformers\transformers.py", line 138, in forward
x = layer(x, attn_mask=attn_mask, length_mask=length_mask)
File "D:\Anaconda\envs\pytorch2\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "D:\Anaconda\envs\pytorch2\lib\site-packages\pytorch_fast_transformers-0.4.0-py3.9-win-amd64.egg\fast_transformers\transformers.py", line 77, in forward
x = x + self.dropout(self.attention(
File "D:\Anaconda\envs\pytorch2\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "D:\Anaconda\envs\pytorch2\lib\site-packages\pytorch_fast_transformers-0.4.0-py3.9-win-amd64.egg\fast_transformers\attention\attention_layer.py", line 103, in forward
new_values = self.inner_attention(
File "D:\Anaconda\envs\pytorch2\lib\site-packages\torch\nn\modules\module.py", line 1501, in call_impl
return forward_call(*args, **kwargs)
File "D:\Anaconda\envs\pytorch2\lib\site-packages\pytorch_fast_transformers-0.4.0-py3.9-win-amd64.egg\fast_transformers\attention\causal_linear_attention.py", line 98, in forward
V = causal_linear(
File "D:\Anaconda\envs\pytorch2\lib\site-packages\pytorch_fast_transformers-0.4.0-py3.9-win-amd64.egg\fast_transformers\attention\causal_linear_attention.py", line 23, in causal_linear
V_new = causal_dot_product(Q, K, V)
File "D:\Anaconda\envs\pytorch2\lib\site-packages\torch\autograd\function.py", line 506, in apply
return super().apply(*args, **kwargs) # type: ignore[misc]
File "D:\Anaconda\envs\pytorch2\lib\site-packages\pytorch_fast_transformers-0.4.0-py3.9-win-amd64.egg\fast_transformers\causal_product_init.py", line 44, in forward
CausalDotProduct.dot[device.type](
TypeError: 'NoneType' object is not callable

[wzk1015]

Please refer to #3.