karpathy/neuraltalk

View on GitHub

NeuralTalk is a Python+numpy project for learning Multimodal Recurrent Neural Networks that describe images with sentences.

Stars: 5.5k
Forks: 1.3k
Open beginner issues: 0
Indexed issues: 26

Dominant language: Python
License: No license data
Last GitHub push: Nov 20, 2015
Latest indexed: Sep 18, 2026
Contributing guide: No contributing guide
Code of conduct: No code of conduct
Beginner labels: No beginner labels indexed
PR merge metrics: No merged PRs in 30d

Open All

26 open issues indexed

Encountered runtime warning while computing logistic function Open

karpathy/neuraltalk#2 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 18, 2026
Aborting, cost seems to be exploding. Open

karpathy/neuraltalk#4 · 4 comments · 0 reactions · 0 assignees · Indexed Sep 18, 2026
R Kelly Open

karpathy/neuraltalk#6 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 18, 2026
Transfer Learning with word2vec? Open

karpathy/neuraltalk#10 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 18, 2026
Best hyperparameters for RNN model Open

karpathy/neuraltalk#18 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 18, 2026
Problems in gradient check Open

karpathy/neuraltalk#19 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 18, 2026
Size of Descriptive Sentences Open

karpathy/neuraltalk#20 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 18, 2026
multiple hosts Open

karpathy/neuraltalk#23 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 18, 2026
py_caffe_feat_extract Open

karpathy/neuraltalk#24 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 18, 2026
training over new dataset Open

karpathy/neuraltalk#25 · 4 comments · 0 reactions · 0 assignees · Indexed Sep 18, 2026
change in extract_features needed due to caffe update Open

karpathy/neuraltalk#31 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 18, 2026
predict_on_images.py: error: too few arguments Open

karpathy/neuraltalk#33 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 18, 2026
Please someone explain the magic behind this Open

karpathy/neuraltalk#35 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 18, 2026
Use for sentence input to sentence output Open

karpathy/neuraltalk#36 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 18, 2026
Confusion about an equation in the paper Open

karpathy/neuraltalk#38 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 18, 2026
Maybe a mistake in lstm_generator.py Open

karpathy/neuraltalk#41 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 18, 2026
How can i use this code to train regions & snippets RNN model? Open

karpathy/neuraltalk#42 · 3 comments · 1 reaction · 0 assignees · Indexed Sep 18, 2026
when i train a batch(batchsize 100) of flickr8k, it takes around 0.8 seconds, Open

karpathy/neuraltalk#43 · 4 comments · 0 reactions · 0 assignees · Indexed Sep 18, 2026
Incorrect prediction while testing. Open

karpathy/neuraltalk#44 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 18, 2026
Why optimizing the Ws matrix directly? Open

karpathy/neuraltalk#45 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 18, 2026
Can we use levelDB features extracted using C++ utility at the place of vgg_feats.mat? Open

karpathy/neuraltalk#46 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 18, 2026
vgg_feats.mat file is being created but its having very small size of 194bytes. Why so? Open

karpathy/neuraltalk#47 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 18, 2026
image captioning Open

karpathy/neuraltalk#48 · 0 comments · 3 reactions · 0 assignees · Indexed Sep 18, 2026
multi-bleu.perl Open

karpathy/neuraltalk#49 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 18, 2026
eval_sentence_predictions.py: error: too few arguments Open

karpathy/neuraltalk#52 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 18, 2026
predict_on_images.py error Open

karpathy/neuraltalk#53 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 18, 2026

karpathy/neuraltalk

Get new issues in your inbox