-
Hi,
It seems that there is not checkpoint file in 'gst_updated/results/100-gumbel_social_transformer-faster_lstm-lr_0.001-init_temp_0.5-edge_head_0-ebd_64-snl_1-snh_8-seed_1000_rand/sj'
when I chang…
-
### Is there an existing issue for this?
- [X] I have searched the existing issues
### Feature Description
The process begins with collecting and preprocessing a large corpus of text data. This dat…
-
python scripts/main.py --cuda 0 --learning_rate 0.0001 --batch_size 16 --epoch 100 --early_stopping 30
Traceback (most recent call last):
File "scripts/main.py…
-
Project Title : Sarcasm Detection Model Comparison
Aim : To determine the best-performing machine learning model for sarcasm detection in headlines by comparing multiple algorithms based on accuracy …
-
### Deep Learning Simplified Repository (Proposing new issue)
:red_circle: **Project Title** : Sarcasm Detection
:red_circle: **Aim**: various deep learning models for detecting sarcasm in text dat…
-
Hi @cspampin, thanks for your great work firstly. Currently, I've trained the model (lstm) in your dataset. But after training for 100 epochs, the model was overfitting, TrL was decreasing while VL an…
-
Hi,
I need to load an old model trained using keras 2.3 (i don't know the tensorflow version), which contains two bidirecitonnal LSTM layers, but it stops at the loading of the first layer.
Is …
-
The model is too slow for real time chat. Perhaps using something faster like Naive Bayes would help.
-
**Is your feature request related to a problem? Please describe.**
Your Seq2SeqSharp project already support LSTMs. Please consider to implement the RWKV large language "linear attention" idea into y…
-
Hello, I am a beginner. Is this the most basic lstm model? Can I use this as a baseline? Or should a more complex model be used?