|
Is teacher forcing default for nn.lstm
|
|
6
|
3649
|
November 12, 2022
|
|
RuntimeError: shape '[-1, 1280, 1]' is invalid for input of size 2776
|
|
0
|
64
|
November 14, 2022
|
|
Error in metric evaluation
|
|
2
|
92
|
November 14, 2022
|
|
MultiheadAttention.forward() got an unexpected keyword argument 'average_attn_weights'
|
|
1
|
71
|
November 13, 2022
|
|
How to convert this code to pytorch format
|
|
1
|
78
|
November 13, 2022
|
|
RNN loss with packed/padded input
|
|
1
|
83
|
November 12, 2022
|
|
Teacher forcing option with PackedSequence input
|
|
1
|
79
|
November 12, 2022
|
|
Tensorflow-esque bucket by sequence length
|
|
25
|
8618
|
November 12, 2022
|
|
How to specify training arguments for huggingface transformer using skorch
|
|
0
|
89
|
November 11, 2022
|
|
How to run with "python3 -m x.y"?
|
|
1
|
66
|
November 10, 2022
|
|
What is the difference between src_mask and src_key_padding_mask
|
|
0
|
82
|
November 8, 2022
|
|
Obtaining outputs and attention weights from intermediate Transformer layers
|
|
7
|
2485
|
November 8, 2022
|
|
How important is saving the state dict of the optimizer?
|
|
1
|
49
|
November 8, 2022
|
|
Transformers for time series forecasting
|
|
1
|
68
|
November 7, 2022
|
|
Pytorch doesn't recognize cuda (cuda 11.7)
|
|
1
|
114
|
November 7, 2022
|
|
Model not learn and i get same results every epoch
|
|
2
|
77
|
November 7, 2022
|
|
Recovering token ids from normalized input?
|
|
8
|
204
|
November 7, 2022
|
|
"Missing token" for time series data
|
|
2
|
93
|
November 6, 2022
|
|
Insert adapters in a transformer
|
|
4
|
144
|
November 6, 2022
|
|
Seq2seq for time series prediction
|
|
0
|
79
|
November 4, 2022
|
|
How to learning to generate a single tensor (2xNxN) from a batch of features?
|
|
1
|
104
|
November 4, 2022
|
|
Graph Neural Networks
|
|
0
|
79
|
November 4, 2022
|
|
Language Models' interpretability
|
|
1
|
54
|
November 3, 2022
|
|
Nonlinearity in TransformerEncoderLayer
|
|
4
|
83
|
November 3, 2022
|
|
having problem with multi-gpu in pytorch transformer
|
|
3
|
79
|
November 3, 2022
|
|
Weird matmul() behavior
|
|
2
|
80
|
November 1, 2022
|
|
Lstm input dimension
|
|
1
|
98
|
October 25, 2022
|
|
Question about Dealing with pad token when computing loss
|
|
0
|
56
|
October 31, 2022
|
|
How do I obtain multiple heads via `multi_head_attention_forward` when using `nn.TransformerEncoder`?
|
|
2
|
401
|
October 29, 2022
|
|
GPU training error!
|
|
2
|
82
|
October 27, 2022
|