search

ijkguo / mx-rcnn

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

training error with latest version (1/20/17) #50

Closed jwnsu closed 7 years ago

jwnsu commented 7 years ago

After checked out latest version (that removed dependency on customized version of mxnet), got following error at the beginning of training:

providing maximum shape [('data', (1, 3, 600, 1000)), ('gt_boxes', (1, 100, 5))] [('label', (1, 20646)), ('bbox_target', (1, 36, 37, 62)), ('bbox_weight', (1, 36, 37, 62))] [20:55:24] /home/dsu/mxnet/dmlc-core/include/dmlc/logging.h:235: [20:55:24] src/symbol/symbol.cc:155: Symbol.InferShapeKeyword argument name bbox_target not found.

Training works fine in previous version. Saw following changes in train_end2end.py that caused the error:

max_data_shape, max_label_shape = train_data.infer_shape(max_data_shape)
max_data_shape.append(('gt_boxes', (input_batch_size, 100, 5)))
print 'providing maximum shape', max_data_shape, max_label_shape

# infer shape
data_shape_dict = dict(train_data.provide_data + train_data.provide_label)
arg_shape, out_shape, aux_shape = sym.infer_shape(**data_shape_dict)  <-- error here
ijkguo commented 7 years ago

Cannot reproduce your issue. Did you change anything?

jwnsu commented 7 years ago

There are only some very minor changes to test on different dataset. Let me pull the source free and see whether we have same error again.

jwnsu commented 7 years ago

After pull fresh source and re-setup, the issue goes away, closing it.