157 questions
-1
votes
1
answer
64
views
How to reconstruct sentences from mean-pooled embeddings (embedding inversion) [closed]
I’m working on a research problem where I want to reconstruct or paraphrase sentences starting from synthetic embeddings.
The embeddings are global (mean-pooled), not token-level, so they lose ...
0
votes
0
answers
32
views
OMX usage in native code to encode and decode frames into h.264 in android
How can we use hardware encoder and decoder for rgb frames convert it to h.264.
in my aosp code hw encoder/decoder is enabled
<MediaCodec name="OMX.qcom.video.encoder.avc" type="...
- 167
0
votes
0
answers
33
views
encoder-decoder sequence-to-sequence time series forecasting
I am building a encoder-decoder sequence-to-sequence model using LSTM on a time series. I am following some tutorials and I am confused as to why do we need to send the previous step prediction as an ...
- 825
0
votes
1
answer
70
views
What is source of this error in time series inference model
Problem: I have created my encoder-decoder model to forecast time series. Model trains well, but I struggle with the error in the inference model and I dont know how to troubleshoot it:
WARNING:...
- 11
1
vote
0
answers
66
views
BucketIterator in Pytorch is putting the batch_size on the torch.shape[1]
Hello guys I m trying to understand how to make a forward pass on an encoder decoder model with a custom dataset.
I have created a BucketIterator to see how the tensor.shape looks like for a batch of ...
1
vote
1
answer
324
views
autoencoder.fit doesnt work becaue of a ValueError
I don't understand what my problem is. It should work, if only because its the standard autoenoder from the tensorflow documentation.
this is the error
line 64, in call
decoded = self.decoder(...
- 11
0
votes
1
answer
175
views
Evaluation of entity relation extraction using encoder decoder?
I am working on relation extraction problem using T5 encoder decoder model with the prefix as 'summary'. I have fine tuned the model but i am confuse about the evaluation metrics to evaluate my ...
0
votes
1
answer
234
views
Encoder - Decoder neural network architecture with different input and output size
I am trying to figure out what would be a good architecture for neural network that takes projections (2D images) from different angles and creates volume consisting of 2D slices (CT-like).
So for ...
- 15
1
vote
0
answers
313
views
Generate prediction sequence with transformers model built from scratch
I'm building a basic transformers models from scratch in PyTorch (with simple tokenization and no masking). I'm using 'The Mysterious Island' by Jules Verne as the training set, so download it from ...
- 3,080
1
vote
1
answer
46
views
train row encoder and column encoder in Tensorflow
I am trying to create a custom neural network that has 2 encoders and one decoder. The row encoder takes in the input of size eg: 30x40 and the column encoder is supposed to take the same data in ...
2
votes
0
answers
589
views
Decoder only architecture to generate embedding vectors
Im currently using models like RoBERTa, CodeBERT etc for "code author identification/ code detection" (you can imagine it like facial recognition task). I know they are encoder architectures....
- 183
1
vote
1
answer
494
views
From_pretrained not loading custom fine-tuned model correctly "encoder weights were not tied to the decoder"
In Google Colab I have loaded a BERT model using the Hugging Face transformers library and then finetuned it using Seq2SeqTrainer. I then saved this model to my Google Drive using model....
1
vote
0
answers
231
views
TFT5ForConditionalGeneration generate returns empty output_scores
I'm fine-tuning the TFT5ForConditionalGeneration model ("t5-small"). Before doing model.fit() and save the model I set the output_score=True as well as the relevant parameters in the ...
- 117
3
votes
1
answer
4k
views
What are differences between T5 and Bart?
I have a question regarding T5 and BART.
It seems they are very similar in the bird's eye view, but I want to know what the differences between them are delicately. As far as I know they are both ...
- 1,459
1
vote
2
answers
172
views
with torch.no_grad() Changes Sequence Length During Evaluation Mode
I built a TransformerEncoder model, and it changes the output's sequence length if I use "with torch.no_grad()" during the evaluation mode.
My model details:
class TransEnc(nn.Module):
...
- 113