No such file model/coco_valid1_eval.pkl

[SilencerChen]

I try to run the test code but couldn't find model/coco_valid1_eval.pkl file. Could you updata it ? Thanks so much.

[YuanEZhou]

I have the same issue. @SilencerChen @gujiuxiang

[gujiuxiang]

@SilencerChen @YuanEZhou, uploaded, pls find the file in Weiyun. Thanks.

[winnechan]

i have create a pkl file that can be loaded without coco_voc by only storing the .details.precision details.score numpy.array.

https://drive.google.com/open?id=1eRrH45xOj41__v2bXMVa8OGZ1Gj6NYze

using python 3 to load the python 2 pkl file:

with open(pickle_file_name, 'rb') as f:
  d = cPickle.load(f, encoding='latin1')

but there's a problem i don't know why: i can get reasonable results by removing the softmax layer in the model.

another problem is that, to me, the output before softmax seems to be the noisy-OR pooling of each image region instance, which can be used to be the final output directly without the score matching of unknown meaning.

can someone explain?