New code example on http://keras.io : multimodal entailment. Train a model to determine if different pieces of content entail or contradict each other, across different input modalities (text & images).https://keras.io/examples/nlp/multimodal_entailment/ …
-
Show this thread
Uses the Google Research multimodal entailment dataset (https://github.com/google-research-datasets/recognizing-multimodal-entailment …). Example created by @RisingSayak!
0 replies
7 retweets
22 likes
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.