-
Hi,
First, i have a little question on my training alignment result, is it normal ? I have this king of graph at step ~3k and the loss decreases and quality of audio is not so bad (a bit metallic) bu…
-
sentence_input = Input(shape=(MAX_SENT_LENGTH,), dtype='int32')
embedded_sequences = embedding_layer(sentence_input)
l_lstm = Bidirectional(GRU(100, return_sequences=True))(embedded_sequences)
l_at…
-
On both sentence (summed and averaged) and words in sentence embeddings
- CNN
- LSTM
- Attention network
- Regression on the embeddings?
- (simple) NN
-
## Environment info
- Platform: Ubuntu 20.04
- Python version: 3.9
- PyTorch version (GPU?): pytorch-lightning==1.5.2
- Using GPU in script?: No
## Information
Model I am using (ListenAt…
-
Hi thanks for work and share. Did you compared CNN with other classifications, such as fasttext or LSTM with attention?
-
im trying convert model (cnn+lstm) from onnx to rknn for rk3588
My code:
shape = (1, 7, 3, 608, 184)
import numpy as np
img_means = (np.array((0.19007764876619865, 0.15170388157131237, 0.106594…
-
大家好,我在按照[这个教程](https://github.com/PaddlePaddle/models/blob/release/2.0-beta/PaddleCV/video/application/video_tag/Run.md)运行video_tag的样例代码时,遇到了如下报错,请问有谁知道什么原因吗?谢谢!
```
(base) user@user-TUF-Gaming-FX50…
wwdok updated
8 months ago
-
I am trying to implement a model using the bayesian lstm layer given I already have a model that relies on lstm and it gets good results for a classification task.
When I use the bayesian layer the l…
-
在跑视频分类attention lstm分类是，发现想测试自己的视频时，需要https://github.com/google/youtube-8m/tree/master/feature_extractor经过youtube-8M抽帧后过一下inception模型，得到视频帧的特征向量，然后在作为attention lstm的输入。
这个为什么这么做，以及以youtube-8M数据集为输入…
stard updated
5 years ago
-
Hi,
Thank you for your example.
I'm trying to use this Attention example in my LSTM model. However, in `def attention layer`, the line
`h = Lambda(lambda X: K.zeros(shape=(K.shape(X)[0], n_h)))(X…