mxnet-model-gallery

mxnet-model-gallery copied to clipboard

My code as follows: > 122 cv::Mat im_ori = cv::imread(image_file, 1); > 123 /* > 124 \* preprocess image as Inception_v3 required > 125 \* crop -> resize -> normlize...

yangzq08

I noticed that there are different image pre-processing pipelines for different models. For [Inception-BN](https://github.com/dmlc/mxnet-model-gallery/blob/master/imagenet-1k-inception-bn.md), the images should be normalized with the `mean_224.nd`: ``` mean_img = mx.nd.load("Inception/mean_224.nd")["mean_img"] normed_img = sample -...

jonbakerfish

Hi When I run classification on an image, i am able to extract the top N predicted tags. I can also extract the 1000 or 21000+ length probability array for...

sourcedexter

Inception V3 gives wrong predictions

18

I guess there is something wrong about the released network or at least the preprocessing code. I tried to use prediction-with-pretrained example but the results are mistaken. I also realized...

erogol

[request] model trained on wikipedia articles

1

The pre-trained imagenet model is super useful. A model pre-trained on wikipedia (or another large text corpus) would be super useful too!

zachmayer