Closed deltheil closed 8 years ago
whoops!
btw Cedric, I haven't verified the outputs for this network yet. I just created it, made sure it runs without errors, that's all. I have to check that outputs are correct, using an example image.
Sure. I made no such assumptions reading the README :)
lol i'm such a mess.
I have to check that outputs are correct, using an example image
@soumith I played a bit with it and the result (with the default dog.jpg
) example sounds correct:
RESULTS (top-5):
----------------
score = 0.999909: n02110341 dalmatian, coach dog, carriage dog (41)
score = 0.000048: n03803284 muzzle (588)
score = 0.000021: n02109047 Great Dane (17)
score = 0.000007: n02100735 English setter (2)
score = 0.000002: n02108089 boxer (130)
See: https://github.com/Moodstocks/inception.torch/commit/1c8f208 (I can send another PR if you are OK with these changes).
@deltheil merged into master! thanks a ton.
Caffe if I remember, is BGR. I think the images have to be swapped. A sanity check would be on the color-specific classes, like an orange or something..
Good point.
I made a quick check with an orange and got:
RESULTS (top-5):
----------------
score = 0.985520: n07747607 orange (319)
score = 0.014264: n07749582 lemon (320)
score = 0.000099: n03134739 croquet ball (756)
score = 0.000026: n07753592 banana (323)
score = 0.000026: n03530642 honeycomb (730)
Looking again at the notebook I can see that the image loading part works with imread from skimage
, and the doc says it returns "an RGB-image as MxNx3".
So I have the feeling everything is OK - I was lucky :)
It might be the new spec of Caffe2?
nice, yea maybe Caffe2 indeed :)
Note: the same problem exists on convnet-benchmarks.