search

open-mmlab / mmfashion

Open-source toolbox for visual fashion analysis based on PyTorch
https://open-mmlab.github.io/
Apache License 2.0
1.26k stars 285 forks source link

Data Preparation Scrips Generate Wrong Landmarks Text #44

Open Eason2Wang opened 4 years ago

Eason2Wang commented 4 years ago

Hi,

When I used prepare_in_shop.py to split deepfashion dataset, I found that the generated landmarks.txt had wrong landmarks data.

1 1 117 067 144 065 073 219 183 210 0 0 0 0 0 0 
143 060 115 059 187 222 074 223 177 211 0 0 0 0 0 0 
155 090 086 245 0 0 0 0 0 0 0 0 0 0 0 0 
1 3 097 056 086 058 153 205 0 0 0 0 0 0 0 0 
3 3 160 063 105 060 168 112 092 104 157 148 104 145 0 0
...

The first two numbers of the 1,4,5 lines are 'clothes type' and 'variation type' but not landmarks.

gyuhwung commented 4 years ago

i get the same issue.. I tried to run inshop-retrieval/ ROI poolling with these, there is no recall improvement compared to global pooling