NeuralBabyTalk
NeuralBabyTalk copied to clipboard
Strange generated captions
Running a pre-trained model on COCO, I'm getting strange predicted captions (examples shown below). Has anyone else run into this issue?
image 60623: wipe jetliner skating doily wipe mustang doing wipe lanterns spoon
image 483108: wipe liner undergoing wipe bike topless wipe baseline bathtub useful wipe adult
image 384213: wipe jetliner doing wipe pancake payer wipe nuts
image 386164: wipe moped tried operate doing at rubs moped spoon
image 223648: wipe moped mustang operate doing at rubs moped jello
image 403385: wipe shamrock doing wipe passenger pancake payer sled
image 294832: wipe shamrock doing wipe pancake passenger payer sled
image 462565: wipe liner undergoing wipe bike topless wipe baseline bathtub useful wipe liner
image 436141: wipe shamrock doing wipe pancake passenger payer preparing
image 192440: wipe shamrock doing wipe passenger payer wipe pancake
Hello, I have the same problem. Have you solved it? This is my captions:
ID:205230 sentence: wipe hull rubs [ kids ] skating carved wipe [ cupcake ]
ID:345136 sentence: wipe civilians [ walker ] skating corsage wipe bins doing wipe prints payer afraid [ cockatoo ]
ID:404613 sentence: wipe [ kid ] horns sprout wipe [ foal ] corsage wipe bins
ID:131089 sentence: wipe chalk [ walker ] horns stitch doing wipe ceramics
ID:432570 sentence: wipe [ biker ] doing who corsage reception skating outdoor wipe tried
ID:214224 sentence: wipe [ jetliner ] horns preparation session wipe southeast doing wipe envelopes rubs [ skateboarded ]
ID:199764 sentence: wipe hull rubs [ bagel ] preparation carved wipe tried doing wipe rugs
ID:176312 sentence: wipe [ jetliner ] preparation corsage dandelion rubs wipe served sprout wipe [ firetruck ]
ID:453297 sentence: wipe [ firetruck ] horns skating outdoor wipe tried bathtub useful wipe terminal
ID:529668 sentence: wipe [ jetliner ] sprout wipe [ firetruck ] corsage dandelion rubs wipe rugs
ID:551107 sentence: wipe civilians [ traffic light ] preparation corsage dandelion rubs wipe [ macbook ]
ID:413120 sentence: wipe inspired [ biker ] fun doing prints removing uneaten
ID:369771 sentence: wipe straining rubs crotch doing wipe [ ski ] rubs crotch payer wipe [ ski ] rubs standing
Hello, I have the same problem. Have you solved it? This is my captions:
ID:205230 sentence: wipe hull rubs [ kids ] skating carved wipe [ cupcake ] ID:345136 sentence: wipe civilians [ walker ] skating corsage wipe bins doing wipe prints payer afraid [ cockatoo ] ID:404613 sentence: wipe [ kid ] horns sprout wipe [ foal ] corsage wipe bins ID:131089 sentence: wipe chalk [ walker ] horns stitch doing wipe ceramics ID:432570 sentence: wipe [ biker ] doing who corsage reception skating outdoor wipe tried ID:214224 sentence: wipe [ jetliner ] horns preparation session wipe southeast doing wipe envelopes rubs [ skateboarded ] ID:199764 sentence: wipe hull rubs [ bagel ] preparation carved wipe tried doing wipe rugs ID:176312 sentence: wipe [ jetliner ] preparation corsage dandelion rubs wipe served sprout wipe [ firetruck ] ID:453297 sentence: wipe [ firetruck ] horns skating outdoor wipe tried bathtub useful wipe terminal ID:529668 sentence: wipe [ jetliner ] sprout wipe [ firetruck ] corsage dandelion rubs wipe rugs ID:551107 sentence: wipe civilians [ traffic light ] preparation corsage dandelion rubs wipe [ macbook ] ID:413120 sentence: wipe inspired [ biker ] fun doing prints removing uneaten ID:369771 sentence: wipe straining rubs crotch doing wipe [ ski ] rubs crotch payer wipe [ ski ] rubs standing
Nope. I starting using other captioning models.
refer this: https://github.com/luulinh90s/Neural-Baby-Talk-python3/issues/2