ryankiros / visual-semantic-embedding

Implementation of the image-sentence embedding method described in "Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models"
Other
426 stars 126 forks source link

HTTP request sent, awaiting response... 403 Forbidden Imagenet VGG19.pkl #12

Open Oushesh opened 5 years ago

Oushesh commented 5 years ago

wget https://s3.amazonaws.com/lasagne/recipes/pretrained/imagenet/vgg19.pkl

I cant access to the imagenet vgg19 which is crucial to using this code implementation. I get access forbidden. Any idea how to I download the .pkl file with wget?

williamwangus commented 5 years ago

I am having the same issues as well.

Oushesh commented 5 years ago

The reason is that the maintainers of thano recipes moved all the serialised pickle models to aws cli. You need to pay for it because of the high bandwidth download spikes.
The other option is to use keras vgg pkl. Write a function to read in the pre trained model and extract the layer weights you need and perform the evaluation.

Oushesh commented 5 years ago

@ryankiros Can you close the issue?