Deeplab training framework crashes on mxnet 0.11.1 version

[chowkamlee81]

Training framework for DeepLab using Deformable convolutions crashes on mxnet 0.11.1. In Deformable-ConvNets-master/deeplab/train.py line no 158. train_net(args, ctx, config.network.pretrained, config.network.pretrained_epoch, config.TRAIN.model_prefix, config.TRAIN.begin_epoch, config.TRAIN.end_epoch, config.TRAIN.lr, config.TRAIN.lr_step) Kindly help me since my job is under trouble Below is the error Traceback (most recent call last): File "/usr/share/pycharm/helpers/pydev/pydevd.py", line 1591, in globals = debugger.run(setup['file'], None, None, is_module) File "/usr/share/pycharm/helpers/pydev/pydevd.py", line 1018, in run pydev_imports.execfile(file, globals, locals) # execute the script File "/home/Softwares/Testing_DC/experiments/deeplab/deeplab_train_test_DC.py", line 21, in train.main() File "/home/Softwares/Testing_DC/experiments/deeplab/../../deeplab/train.py", line 159, in main config.TRAIN.begin_epoch, config.TRAIN.end_epoch, config.TRAIN.lr, config.TRAIN.lr_step) File "/home/Softwares/Testing_DC/experiments/deeplab/../../deeplab/train.py", line 153, in train_net arg_params=arg_params, aux_params=aux_params, begin_epoch=begin_epoch, num_epoch=end_epoch) File "/home/Softwares/Testing_DC/experiments/deeplab/../../deeplab/core/module.py", line 948, in fit for_training=True, force_rebind=force_rebind) File "/home/Softwares/Testing_DC/experiments/deeplab/../../deeplab/core/module.py", line 841, in bind for_training, inputs_need_grad, force_rebind=False, shared_module=None) File "/home/Softwares/Testing_DC/experiments/deeplab/../../deeplab/core/module.py", line 396, in bind state_names=self._state_names) File "/home/Softwares/Testing_DC/experiments/deeplab/../../deeplab/core/DataParallelExecutorGroup.py", line 183, in init self.bind_exec(data_shapes, label_shapes, shared_group) File "/home/Softwares/Testing_DC/experiments/deeplab/../../deeplab/core/DataParallelExecutorGroup.py", line 283, in bind_exec shared_group)) File "/home/Softwares/Testing_DC/experiments/deeplab/../../deeplab/core/DataParallelExecutorGroup.py", line 500, in _bind_ith_exec argshapes, , aux_shapes = self.symbol.infer_shape(*input_shapes) File "/usr/local/lib/python2.7/dist-packages/mxnet-0.11.1-py2.7.egg/mxnet/symbol/symbol.py", line 962, in infer_shape res = self._infer_shape_impl(False, args, **kwargs) File "/usr/local/lib/python2.7/dist-packages/mxnet-0.11.1-py2.7.egg/mxnet/symbol/symbol.py", line 1058, in _infer_shape_impl "but '%s' is %s." % (k, type(v))) TypeError: Arguments need to be shapes (tuple), but 'label' is <type 'list'>.

[HaozhiQi]

MXNet changed the interface. Please use MXNet's commit version 62ecb60

[chowkamlee81]

thanks.....