search

sanghoon / pva-faster-rcnn

Demo code for PVANet
https://arxiv.org/abs/1611.08588
Other
651 stars 241 forks source link

example_fine_tuning #52

Closed solemnrole closed 7 years ago

solemnrole commented 7 years ago

i use the train.prototxt in this Catalog,the dataset is VOC07trainval+07test,pretrain model is the test.model,itering 14000 times,the loss is always too large(40.)i dont know why.

MyVanitar commented 7 years ago

@solemnrole May I ask you how did you create imdb file for your custom dataset to train on PVANET?

solemnrole commented 7 years ago

@VanitarNordic pvanet doest seem to need your orignal custom datasets is lmdb ,and you just need to do is making your dataset follwing VOC style.

MyVanitar commented 7 years ago

@solemnrole By following the VOC style, each image would have its own corresponding .xml file, BUT according to this example, for training we should create an IMDB file which contains the information of both training and validation images:

https://github.com/sanghoon/pva-faster-rcnn/tree/master/models/pvanet/example_train

solemnrole commented 7 years ago

@VanitarNordic that is what you should do! make your each image would have its own corresponding .xml file. the pvanet will transform your VOC style datasets into lmdb!

MyVanitar commented 7 years ago

@solemnrole wow, I already have bunch of images and their annotations in .xml, may I ask you which file in the repository will convert these to an IMDB file?

MyVanitar commented 7 years ago

@solemnrole waiting for you ...

solemnrole commented 7 years ago

@VanitarNordic i am sorry, pvanet will not transform your datasets into lmdb, see get_minibatch.py for details.

MyVanitar commented 7 years ago

@solemnrole

Yes, actually before training, we have to convert our dada-set to IMDB, as it is one of the input parameters here: https://github.com/sanghoon/pva-faster-rcnn/tree/master/models/pvanet/example_train