search

ijkguo / mx-rcnn

Parallel Faster R-CNN implementation with MXNet.
Other
671 stars 290 forks source link

problem python train_alternate.py --gpus 0. #32

Closed darrylbobo closed 7 years ago

darrylbobo commented 7 years ago

Hi, when I ran python train_alternate.py --gpus 0.

it reported error as below:

libdc1394 error: Failed to initialize libdc1394 INFO:root:########## TRAIN RPN WITH IMAGENET INIT voc_2007_trainval gt roidb loaded from /mxnet/example/rcnn/data/cache/voc_2007_trainval_gt_roidb.pkl append flipped images to roidb prepare roidb providing maximum shape [('data', (1, 3, 1000, 1000))] [('label', (1, 34596)), ('bbox_target', (1, 36, 62, 62)), ('bbox_inside_weight', (1, 36, 62, 62)), ('bbox_outside_weight', (1, 36, 62, 62))] Traceback (most recent call last): File "train_alternate.py", line 104, in args.frequent, args.kv_store, args.work_load_list) File "train_alternate.py", line 26, in alternate_train 'model/rpn1', ctx, begin_epoch, rpn_epoch, frequent, kv_store, work_load_list) File "/mxnet/example/rcnn/tools/train_rpn.py", line 54, in train_rpn args, auxs = load_param(pretrained, epoch, convert=True) ValueError: too many values to unpack

ijkguo commented 7 years ago

Thanks for reporting this. It needs a while to update that. Right now just change it to args, auxs, _ = load_param(pretrained, epoch, convert=True)

ijkguo commented 7 years ago

The third parameter is num_classes. Updates to mxnet/example need a while to verify. You could also try this repo.

ijkguo commented 7 years ago

This has been resolved in dmlc/mxnet