Skip to content

Releases: danieljl/keras-image-captioning

Pretrained Model

15 Apr 12:14
@danieljl danieljl
v1
cac7a99
Compare
Choose a tag to compare
Pretrained Model Latest
Latest

Copy model-weights.hdf5 to keras-image-captioning/results/flickr8k/final-model.

Now you can run an inference from that checkpoint by executing a command below from keras-image-captioning directory:

python -m keras_image_captioning.inference \
  --dataset-type test \
  --method beam_search \
  --beam-size 3 \
  --training-dir results/flickr8k/final-model
Assets 3
Loading