-
Hello,
When loading weights from a pretrained PyTorch model using the `VarBuilder::get` method, I've noticed that most of the loaded weights for different layers match correctly, except for a 2 lay…
-
This issue came up while implementing an Encoder-Decoder ConvLSTM, but I think is applicable to all kind of RNNs in Lux.
The approach I'm following is to feed the encoder with my input `x`, obtain `(…
-
The paper - Semi-supervised Sequence Learning(https://arxiv.org/abs/1511.01432) - states that for training of SA-LSTM, they used the same LSTM for both encoding and for decoding. However, this impleme…
-
COMMAND: python main.py --encoder cnn --decoder rnn --encoder-dropout 0.05 --decoder-dropout 0.2
Namespace(batch_size=1, cuda=True, decoder='rnn', decoder_dropout=0.2, decoder_hidden=256, dims=6, …
-
I cannot _sheeprl-eval_ my trained model, since the keys in the world model's state_dict have different names:
Stacktrace
Error executing job with overrides: ['checkpoint_path=/home/drt/Deskto…
-
Please, please, consider adding the ssm_state input parameter for selective_scan_fn to allow hidden state initialisation for the Mamba block.
Also please consider making hidden state differentiable a…
-
Hi,
I downloaded `hierdec-mel_16bar` checkpoint from [magentadata]( https://storage.googleapis.com/magentadata/models/music_vae/checkpoints/hierdec-mel_16bar.tar).
I was attempting to continue t…
-
size mismatch for encoder_proj.weight: copying a param with shape torch.Size([128, 512]) from checkpoint, the shape in current model is torch.Size([128, 1024]).
size mismatch for decoder.attn_rnn.wei…
-
It works perfectly fine with the Greedy decoder. Here is the code
Tensorflow: 1.8.0
```
encoder_emb_inp = tf.nn.embedding_lookup(embeddings, x)
encoder_cell = rnn.GRUCell(rnn_size,name='encoder…
-
In my opinion this is the crown jewel lab of the whole NLP course of the Machine Learning Engineer learning path. The CSB (Cloud Skills Boost) lab is titled simply "Encoder decoder" (https://www.cloud…