Show_and_Tell
Show_and_Tell copied to clipboard
Show and Tell : A Neural Image Caption Generator
I use the pre-trianed weights provided [here](https://ucsb.app.box.com/s/vqcxockfzoxfqltrg4l619x1cfvnskog) , but I just could achieve the results below Bleu_1: 0.524 Bleu_2: 0.303 Bleu_3: 0.156 Bleu_4: 0.082
hi, can you share with me the final train model ? thanks!
Overfit
How do I know if my model is overfitted?
thanks for public the code, my question is what is the version of tensorflow is available, thanks
Hello, If you have any docker image, could you please make it available? thank you!
Hello, I can successfully load the model [289999.npy](https://app.box.com/s/xuigzzaqfbpnf76t295h109ey9po5t8p), but when I tried with the model 39999.npy provided here, I've got a shape error: ValueError: Dimension 0 in both shapes must...
hi, if I only want to test this pretrained model(39999.npy) on new images, may I need to download the ms coco dataset?
Hi, Can you upload your final trained model. Also, did you train your model on the Flickr (8k or 30k) dataset as well? Thanks Rahul.