ShaoqingRen / SPP_net

SPP_net : Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
363 stars 236 forks source link

when i run spp_exp_train_and_test_voc(opts), there is a error #45

Open wuxinhong opened 9 years ago

wuxinhong commented 9 years ago

when i run spp_exp_train_and_test_voc(opts), there is a error eval_voc (line 82) 输入参数太多。

出错 spp_test>(parfor body) (line 171) res(model_ind) = imdb.eval_func(cls, aboxes{model_ind}, imdb, cache_name, suffix, fast);

出错 spp_test (line 169) parfor model_ind = 1:num_classes, lately ,i found the problem come from this Program in the spp_exp_train_and_test_voc m file ,res_test = spp_test(spp_model, opts.imdb_test, opts.roidb_test, opts.feat_cache_test, '', true), anyone help me??

okhiwell commented 9 years ago

Is there any requirements about the memory for your computer when you run the script "experiments/Script_spp_voc"

ShaoqingRen commented 9 years ago

@wuxinhong We provide a function in SPP_net/datasets/VOCdevkit2007/VOCcode, which added a param

ShaoqingRen commented 9 years ago

@ct1104,

The memory for voc07, maybe around 16G. To save memory, you can set the data_param.iter_per_batch in spp_finetune_voc.m to a smaller number.

okhiwell commented 9 years ago

thank you for your answering,I will have a try!

On Mon, Apr 27, 2015 at 3:58 PM, Shaoqing Ren notifications@github.com wrote:

@ct1104 https://github.com/ct1104,

The memory for voc07, maybe around 16G. To save memory, you can set the data_param.iter_per_batch in spp_finetune_voc.m to a smaller number.

— Reply to this email directly or view it on GitHub https://github.com/ShaoqingRen/SPP_net/issues/45#issuecomment-96545248.