-
do u have tested the text feature from char-CNN-RNN and skip-thought? and which is better for generating images?
-
- [x] Install [warp-transducer](https://github.com/HawkAaron/warp-transducer) in Dockerfile - see https://github.com/ryanleary/mlperf-rnnt-ref/issues/1#issuecomment-559186425.
- [x] Correct `forward…
samgd updated
4 years ago
-
Hi VDelv,
thank you for sharing this implementation publicly.
I wanted to ask about the `Mix` model of the multi frame approach (CNN + LSTM + 1d CONV).
the authors mentioned LSTM layer, yet the imp…
-
Hi,
Thanks for your code again. I changed the number of layers from 3 to 1 for my data. and when I want to test the retrained model, I got this error. "RuntimeError: Error(s) in loading state_dict fo…
-
In keras or tensorflow, LSTM or RNN support masking which uses a mask value to skip timesteps. This is commonly used in some state-of-the-art models such as keras-bert. So we may need support masking …
-
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…
-
I have met some problems when implements the RNN-LSTM model, the error is very huge when the part of known trips is short, for instance, only the arrival time of the first stop is known, the predicti…
-
james@:~/ai/AI_Composer$ python main.py
Traceback (most recent call last):
File "main.py", line 4, in
import rnn
File "/home/james/ai/AI_Composer/rnn.py", line 16, in
from model import M…
-
Right now the RNN CTC model in `rnn_ctc.py` has the class name `Model` and inherits from `model.Model`. I find this to be confusing and I propose that we rename the `rnn_ctc.Model` class and provide t…
-
make sure that the function call for predict is directly on the model (that it is compatible with rnn-theorist)
- [x] disagreement
- [x] falsification
Make sure that the predict method is called wit…