search

CSAILVision / NetDissect-Lite

Light version of Network Dissection for Quantifying Interpretability of Networks
215 stars 52 forks source link

Different Layers, Same results #17

Open rahimentezari opened 4 years ago

rahimentezari commented 4 years ago

I trained a VGG-16 for CIFAR10, 32x32 pixels. When I run netdissect for different Conv layers, e.g. conv1 and conv13, I got the same results. Should it be like this? I got the same results for both : (['grass', 'sky', 'zigzagged', 'striped', 'chequered', 'banded', 'waffled', 'freckled', 'red-c', 'blue-c'], [1, 1, 19, 14, 14, 10, 1, 1, 1, 1], [('object', 2), ('scene', 0), ('part', 0), ('material', 0), ('texture', 6), ('color', 2)], 100, 12, True, 'result/pytorch_vgg16_cifar10/html/image/conv1-bargraph.svg')

cyizhuo commented 4 years ago

Hello friend, did you sloved this problem? I'm having the same problem now.

By the way, I saw you made a Broden dataset with CIFAR-10, does it have semantic segmentation like the original Broden?

Thank you for answering.