Cannot start training vgg16_reduced

[ssdevel]

python train.py --num-class 1 --class-name billboard --num-example 936 --train-path records\25_train.rec --val-path records\25_val.rec --gpus 0 --batch-size 16 C:\Users\stefa\Anaconda2\lib\site-packages\h5py_init_.py:36: FutureWarning: Conversion of the second argument of issubdtype from float to np.floating is deprecated. In future, it will be treated as np.float64 == np.dtype(float).type. from ._conv import register_converters as register_converters Using mxnet as: <module 'mxnet' from 'C:\Users\stefa\Anaconda2\lib\site-packages\mxnet_init.pyc'> Warning: using pre-installed version of mxnet may cause unexpected error... (export MXNET_EXAMPLE_SSD_DISABLE_PRE_INSTALLED=1) to prevent loading pre-installed mxnet. [21:10:37] c:\jenkins\workspace\mxnet-tag\mxnet\src\io\iter_image_det_recordio.cc:281: ImageDetRecordIOParser: records\25_train.rec, use 7 threads for decoding.. [21:10:38] c:\jenkins\workspace\mxnet-tag\mxnet\src\io\iter_image_det_recordio.cc:334: ImageDetRecordIOParser: records\25_train.rec, label padding width: 350 [21:10:46] c:\jenkins\workspace\mxnet-tag\mxnet\src\io\iter_image_det_recordio.cc:281: ImageDetRecordIOParser: records\25_val.rec, use 7 threads for decoding.. [21:10:46] c:\jenkins\workspace\mxnet-tag\mxnet\src\io\iter_image_det_recordio.cc:334: ImageDetRecordIOParser: records\25_val.rec, label padding width: 350 INFO:root:Start training with (gpu(0)) from pretrained model C:\Users\stefa\Desktop\mxnet-ssd-master\model\vgg16_reduced [21:10:49] c:\jenkins\workspace\mxnet-tag\mxnet\src\nnvm\legacy_json_util.cc:209: Loading symbol saved by previous version v0.9.5. Attempting to upgrade... [21:10:49] c:\jenkins\workspace\mxnet-tag\mxnet\src\nnvm\legacy_json_util.cc:217: Symbol successfully upgraded! INFO:root:Freezed parameters: [conv1_1_weight,conv1_1_bias,conv1_2_weight,conv1_2_bias,conv2_1_weight,conv2_1_bias,conv2_2_weight,conv2_2_bias] Traceback (most recent call last): File "train.py", line 149, in tensorboard=args.tensorboard) File "C:\Users\stefa\Desktop\mxnet-ssd-master\train\train_net.py", line 355, in train_net monitor=monitor) File "C:\Users\stefa\Anaconda2\lib\site-packages\mxnet\module\base_module.py", line 488, in fit allow_missing=allow_missing, force_init=force_init) File "C:\Users\stefa\Anaconda2\lib\site-packages\mxnet\module\module.py", line 309, in init_params _impl(desc, arr, arg_params) File "C:\Users\stefa\Anaconda2\lib\site-packages\mxnet\module\module.py", line 297, in _impl cache_arr.copyto(arr) File "C:\Users\stefa\Anaconda2\lib\site-packages\mxnet\ndarray\ndarray.py", line 1970, in copyto return _internal._copyto(self, out=other) File "", line 25, in _copyto File "C:\Users\stefa\Anaconda2\lib\site-packages\mxnet_ctypes\ndarray.py", line 92, in _imperative_invoke ctypes.byref(out_stypes))) File "C:\Users\stefa\Anaconda2\lib\site-packages\mxnet\base.py", line 149, in check_call raise MXNetError(py_str(_LIB.MXGetLastError())) mxnet.base.MXNetError: [21:10:53] c:\jenkins\workspace\mxnet-tag\mxnet\src\operator\elemwise_op_common.h:123: Check failed: assign(&dattr, (*vec)[i]) Incompatible attr in node at 0-th output: expected [84], got [8]

[Belinda-great]

i think the num_filters is not right, you can check it.