MXNetError when I tried to run python ./rfcn/demo.py

zhangboshen commented 7 years ago

zhangboshen@smart-gpu-server1:~/src/mxnet/Deformable-ConvNets$ python ./rfcn/demo.py {'CLASS_AGNOSTIC': True, 'MXNET_VERSION': 'mxnet', 'SCALES': [(600, 1000)], 'TEST': {'BATCH_IMAGES': 1, 'CXX_PROPOSAL': False, 'HAS_RPN': True, 'NMS': 0.3, 'PROPOSAL_MIN_SIZE': 0, 'PROPOSAL_NMS_THRESH': 0.7, 'PROPOSAL_POST_NMS_TOP_N': 2000, 'PROPOSAL_PRE_NMS_TOP_N': 20000, 'RPN_MIN_SIZE': 0, 'RPN_NMS_THRESH': 0.7, 'RPN_POST_NMS_TOP_N': 300, 'RPN_PRE_NMS_TOP_N': 6000, 'max_per_image': 100, 'test_epoch': 8}, 'TRAIN': {'ALTERNATE': {'RCNN_BATCH_IMAGES': 0, 'RPN_BATCH_IMAGES': 0, 'rfcn1_epoch': 0, 'rfcn1_lr': 0, 'rfcn1_lr_step': '', 'rfcn2_epoch': 0, 'rfcn2_lr': 0, 'rfcn2_lr_step': '', 'rpn1_epoch': 0, 'rpn1_lr': 0, 'rpn1_lr_step': '', 'rpn2_epoch': 0, 'rpn2_lr': 0, 'rpn2_lr_step': '', 'rpn3_epoch': 0, 'rpn3_lr': 0, 'rpn3_lr_step': ''}, 'ASPECT_GROUPING': True, 'BATCH_IMAGES': 1, 'BATCH_ROIS': -1, 'BATCH_ROIS_OHEM': 128, 'BBOX_MEANS': [0.0, 0.0, 0.0, 0.0], 'BBOX_NORMALIZATION_PRECOMPUTED': True, 'BBOX_REGRESSION_THRESH': 0.5, 'BBOX_STDS': [0.1, 0.1, 0.2, 0.2], 'BBOX_WEIGHTS': array([ 1., 1., 1., 1.]), 'BG_THRESH_HI': 0.5, 'BG_THRESH_LO': 0.0, 'CXX_PROPOSAL': False, 'ENABLE_OHEM': True, 'END2END': True, 'FG_FRACTION': 0.25, 'FG_THRESH': 0.5, 'FLIP': True, 'RESUME': True, 'RPN_BATCH_SIZE': 256, 'RPN_BBOX_WEIGHTS': [1.0, 1.0, 1.0, 1.0], 'RPN_CLOBBER_POSITIVES': False, 'RPN_FG_FRACTION': 0.5, 'RPN_MIN_SIZE': 0, 'RPN_NEGATIVE_OVERLAP': 0.3, 'RPN_NMS_THRESH': 0.7, 'RPN_POSITIVE_OVERLAP': 0.7, 'RPN_POSITIVE_WEIGHT': -1.0, 'RPN_POST_NMS_TOP_N': 300, 'RPN_PRE_NMS_TOP_N': 6000, 'SHUFFLE': True, 'begin_epoch': 5, 'end_epoch': 8, 'lr': 0.0005, 'lr_factor': 0.1, 'lr_step': '5.333', 'model_prefix': 'e2e', 'momentum': 0.9, 'warmup': False, 'warmup_lr': 5e-05, 'warmup_step': 1000, 'wd': 0.0005}, 'dataset': {'NUM_CLASSES': 81, 'dataset': 'coco', 'dataset_path': './data/coco', 'image_set': 'train2014+val2014', 'proposal': 'rpn', 'root_path': './data', 'test_image_set': 'test-dev2015'}, 'default': {'frequent': 20, 'kvstore': 'device'}, 'gpus': '0', 'network': {'ANCHOR_RATIOS': [0.5, 1, 2], 'ANCHOR_SCALES': [4, 8, 16, 32], 'FIXED_PARAMS': ['conv1', 'bn_conv1', 'res2', 'bn2', 'gamma', 'beta'], 'FIXED_PARAMS_SHARED': ['conv1', 'bn_conv1', 'res2', 'bn2', 'res3', 'bn3', 'res4', 'bn4', 'gamma', 'beta'], 'IMAGE_STRIDE': 0, 'NUM_ANCHORS': 12, 'PIXEL_MEANS': array([ 103.06, 115.9 , 123.15]), 'RCNN_FEAT_STRIDE': 16, 'RPN_FEAT_STRIDE': 16, 'pretrained': './model/pretrained_model/resnet_v1_101', 'pretrained_epoch': 0}, 'output_path': './output/rfcn', 'symbol': 'resnet_v1_101_rfcn'} [16:21:10] /home/zhangboshen/mxnet/dmlc-core/include/dmlc/logging.h:304: [16:21:10] src/c_api/c_api_ndarray.cc:385: Operator _zeros cannot be run; requires at least one of FCompute, NDArrayFunction, FCreateOperator be registered

Stack trace returned 10 entries: [bt] (0) /home/zhangboshen/anaconda2/lib/python2.7/site-packages/mxnet-0.10.1-py2.7.egg/mxnet/libmxnet.so(_ZN4dmlc15LogMessageFatalD1Ev+0x3c) [0x7f0e1ff9981c] [bt] (1) /home/zhangboshen/anaconda2/lib/python2.7/site-packages/mxnet-0.10.1-py2.7.egg/mxnet/libmxnet.so(Z20ImperativeInvokeImplRKN4nnvm9NodeAttrsEiPPvPiPS4+0xaca) [0x7f0e209c35da] [bt] (2) /home/zhangboshen/anaconda2/lib/python2.7/site-packages/mxnet-0.10.1-py2.7.egg/mxnet/libmxnet.so(MXImperativeInvoke+0x142) [0x7f0e209c3d52] [bt] (3) /home/zhangboshen/anaconda2/lib/python2.7/lib-dynload/_ctypes.so(ffi_call_unix64+0x4c) [0x7f0e10a9531c] [bt] (4) /home/zhangboshen/anaconda2/lib/python2.7/lib-dynload/_ctypes.so(ffi_call+0x1f5) [0x7f0e10a94a75] [bt] (5) /home/zhangboshen/anaconda2/lib/python2.7/lib-dynload/_ctypes.so(_ctypes_callproc+0x3e6) [0x7f0e10a8c126] [bt] (6) /home/zhangboshen/anaconda2/lib/python2.7/lib-dynload/_ctypes.so(+0x9ce3) [0x7f0e10a83ce3] [bt] (7) /home/zhangboshen/anaconda2/bin/../lib/libpython2.7.so.1.0(PyObject_Call+0x53) [0x7f0e2e401dc3] [bt] (8) /home/zhangboshen/anaconda2/bin/../lib/libpython2.7.so.1.0(PyEval_EvalFrameEx+0x6a67) [0x7f0e2e4b36c7] [bt] (9) /home/zhangboshen/anaconda2/bin/../lib/libpython2.7.so.1.0(PyEval_EvalCodeEx+0x89e) [0x7f0e2e4b61ce]

Traceback (most recent call last): File "./rfcn/demo.py", line 130, in main() File "./rfcn/demo.py", line 90, in main arg_params=arg_params, aux_params=aux_params) File "/home/zhangboshen/src/mxnet/Deformable-ConvNets/rfcn/core/tester.py", line 29, in init self._mod.bind(provide_data, provide_label, for_training=False) File "/home/zhangboshen/src/mxnet/Deformable-ConvNets/rfcn/core/module.py", line 839, in bind for_training, inputs_need_grad, force_rebind=False, shared_module=None) File "/home/zhangboshen/src/mxnet/Deformable-ConvNets/rfcn/core/module.py", line 396, in bind state_names=self._state_names) File "/home/zhangboshen/src/mxnet/Deformable-ConvNets/rfcn/core/DataParallelExecutorGroup.py", line 186, in init self.bind_exec(data_shapes, label_shapes, shared_group) File "/home/zhangboshen/src/mxnet/Deformable-ConvNets/rfcn/core/DataParallelExecutorGroup.py", line 272, in bind_exec shared_group)) File "/home/zhangboshen/src/mxnet/Deformable-ConvNets/rfcn/core/DataParallelExecutorGroup.py", line 545, in _bind_ith_exec context, self.logger) File "/home/zhangboshen/src/mxnet/Deformable-ConvNets/rfcn/core/DataParallelExecutorGroup.py", line 523, in _get_or_reshape arg_arr = nd.zeros(arg_shape, context, dtype=arg_type) File "/home/zhangboshen/anaconda2/lib/python2.7/site-packages/mxnet-0.10.1-py2.7.egg/mxnet/ndarray.py", line 1028, in zeros return _internal._zeros(shape=shape, ctx=ctx, dtype=dtype, kwargs) File "", line 15, in _zeros File "/home/zhangboshen/anaconda2/lib/python2.7/site-packages/mxnet-0.10.1-py2.7.egg/mxnet/_ctypes/ndarray.py", line 73, in _imperative_invoke c_array(ctypes.c_char_p, [c_str(str(val)) for val in vals]))) File "/home/zhangboshen/anaconda2/lib/python2.7/site-packages/mxnet-0.10.1-py2.7.egg/mxnet/base.py", line 85, in check_call raise MXNetError(py_str(_LIB.MXGetLastError())) _mxnet.base.MXNetError: [16:21:10] src/c_api/c_api_ndarray.cc:385: Operator zeros cannot be run; requires at least one of FCompute, NDArrayFunction, FCreateOperator be registered**

Stack trace returned 10 entries: [bt] (0) /home/zhangboshen/anaconda2/lib/python2.7/site-packages/mxnet-0.10.1-py2.7.egg/mxnet/libmxnet.so(_ZN4dmlc15LogMessageFatalD1Ev+0x3c) [0x7f0e1ff9981c] [bt] (1) /home/zhangboshen/anaconda2/lib/python2.7/site-packages/mxnet-0.10.1-py2.7.egg/mxnet/libmxnet.so(Z20ImperativeInvokeImplRKN4nnvm9NodeAttrsEiPPvPiPS4+0xaca) [0x7f0e209c35da] [bt] (2) /home/zhangboshen/anaconda2/lib/python2.7/site-packages/mxnet-0.10.1-py2.7.egg/mxnet/libmxnet.so(MXImperativeInvoke+0x142) [0x7f0e209c3d52] [bt] (3) /home/zhangboshen/anaconda2/lib/python2.7/lib-dynload/_ctypes.so(ffi_call_unix64+0x4c) [0x7f0e10a9531c] [bt] (4) /home/zhangboshen/anaconda2/lib/python2.7/lib-dynload/_ctypes.so(ffi_call+0x1f5) [0x7f0e10a94a75] [bt] (5) /home/zhangboshen/anaconda2/lib/python2.7/lib-dynload/_ctypes.so(_ctypes_callproc+0x3e6) [0x7f0e10a8c126] [bt] (6) /home/zhangboshen/anaconda2/lib/python2.7/lib-dynload/_ctypes.so(+0x9ce3) [0x7f0e10a83ce3] [bt] (7) /home/zhangboshen/anaconda2/bin/../lib/libpython2.7.so.1.0(PyObject_Call+0x53) [0x7f0e2e401dc3] [bt] (8) /home/zhangboshen/anaconda2/bin/../lib/libpython2.7.so.1.0(PyEval_EvalFrameEx+0x6a67) [0x7f0e2e4b36c7] [bt] (9) /home/zhangboshen/anaconda2/bin/../lib/libpython2.7.so.1.0(PyEval_EvalCodeEx+0x89e) [0x7f0e2e4b61ce]

HaozhiQi commented 7 years ago

Please compile MXNet with Cuda enabled.

zhangboshen commented 7 years ago

thanks! but I still got a problem when I compile MXNet with USE_CUDE=1

/home/zhangboshen/mxnet/mshadow/mshadow/./base.h(359): error: identifier "CUDA_R_32I" is undefined

/home/zhangboshen/mxnet/mshadow/mshadow/./base.h(359): error: identifier "CUDA_R_32I" is undefined

1 error detected in the compilation of "/tmp/tmpxft_00003344_00000000-17_count_sketch.compute_61.cpp1.ii". make: [build/src/operator/contrib/count_sketch_gpu.o] Error 2 make: Waiting for unfinished jobs.... 1 error detected in the compilation of "/tmp/tmpxft_00003337_00000000-17_multibox_prior.compute_61.cpp1.ii". 1 error detected in the compilation of "/tmp/tmpxft_00003325_00000000-17_dequantize.compute_61.cpp1.ii". make: [build/src/operator/contrib/multibox_prior_gpu.o] Error 2 make: [build/src/operator/contrib/dequantize_gpu.o] Error 2 1 error detected in the compilation of "/tmp/tmpxft_0000333d_00000000-17_elemwise_sum.compute_61.cpp1.ii". 1 error detected in the compilation of "/tmp/tmpxft_00003364_00000000-17_fft.compute_61.cpp1.ii". 1 error detected in the compilation of "/tmp/tmpxft_00003341_00000000-17_ifft.compute_61.cpp1.ii". make: [build/src/operator/tensor/elemwise_sum_gpu.o] Error 2 1 error detected in the compilation of "/tmp/tmpxft_00003329_00000000-17_deformable_psroi_pooling.compute_61.cpp1.ii". make: [build/src/operator/contrib/fft_gpu.o] Error 2 make: [build/src/operator/contrib/ifft_gpu.o] Error 2 make: [build/src/operator/contrib/deformable_psroi_pooling_gpu.o] Error 2 1 error detected in the compilation of "/tmp/tmpxft_0000335e_00000000-17_psroi_pooling.compute_61.cpp1.ii". make: [build/src/operator/contrib/psroi_pooling_gpu.o] Error 2 1 error detected in the compilation of "/tmp/tmpxft_0000339c_00000000-17_multibox_detection.compute_61.cpp1.ii". make: [build/src/operator/contrib/multibox_detection_gpu.o] Error 2 1 error detected in the compilation of "/tmp/tmpxft_00003391_00000000-17_native_op.compute_61.cpp1.ii". make: [build/src/operator/custom/native_op_gpu.o] Error 2 1 error detected in the compilation of "/tmp/tmpxft_0000333c_00000000-17_ctc_loss.compute_61.cpp1.ii". make: [build/src/operator/contrib/ctc_loss_gpu.o] Error 2 1 error detected in the compilation of "/tmp/tmpxft_000033b4_00000000-17_elemwise_binary_op_basic.compute_61.cpp1.ii". make: [build/src/operator/tensor/elemwise_binary_op_basic_gpu.o] Error 2 1 error detected in the compilation of "/tmp/tmpxft_000033a3_00000000-17_deformable_convolution.compute_61.cpp1.ii". 1 error detected in the compilation of "/tmp/tmpxft_000033b2_00000000-17_quantize.compute_61.cpp1.ii". make: [build/src/operator/contrib/deformable_convolution_gpu.o] Error 2 make: [build/src/operator/contrib/quantize_gpu.o] Error 2 1 error detected in the compilation of "/tmp/tmpxft_000033ce_00000000-17_elemwise_binary_op_logic.compute_61.cpp1.ii". 1 error detected in the compilation of "/tmp/tmpxft_0000335b_00000000-17_elemwise_binary_scalar_op_logic.compute_61.cpp1.ii". make: [build/src/operator/tensor/elemwise_binary_op_logic_gpu.o] Error 2 make: [build/src/operator/tensor/elemwise_binary_scalar_op_logic_gpu.o] Error 2 1 error detected in the compilation of "/tmp/tmpxft_0000337e_00000000-17_proposal.compute_61.cpp1.ii". 1 error detected in the compilation of "/tmp/tmpxft_000033b7_00000000-17_multibox_target.compute_61.cpp1.ii". 1 error detected in the compilation of "/tmp/tmpxft_000033e7_00000000-17_sample_multinomial_op.compute_61.cpp1.ii". 1 error detected in the compilation of "/tmp/tmpxft_00003402_00000000-17_elemwise_binary_broadcast_op_logic.compute_61.cpp1.ii". 1 error detected in the compilation of "/tmp/tmpxft_000033d9_00000000-17_sample_op.compute_61.cpp1.ii". make: [build/src/operator/random/sample_multinomial_op_gpu.o] Error 2 make: [build/src/operator/contrib/multibox_target_gpu.o] Error 2 make: [build/src/operator/tensor/elemwise_binary_broadcast_op_logic_gpu.o] Error 2 make: [build/src/operator/contrib/proposal_gpu.o] Error 2 make: [build/src/operator/random/sample_op_gpu.o] Error 2 1 error detected in the compilation of "/tmp/tmpxft_00003396_00000000-17_elemwise_binary_op_extended.compute_61.cpp1.ii". 1 error detected in the compilation of "/tmp/tmpxft_00003372_00000000-17_softmax.compute_61.cpp1.ii". 1 error detected in the compilation of "/tmp/tmpxft_000033a8_00000000-17_control_flow_op.compute_61.cpp1.ii". make: [build/src/operator/tensor/elemwise_binary_op_extended_gpu.o] Error 2 make: [build/src/operator/nn/softmax_gpu.o] Error 2 make: [build/src/operator/tensor/control_flow_op_gpu.o] Error 2 1 error detected in the compilation of "/tmp/tmpxft_0000337f_00000000-17_broadcast_reduce_op_index.compute_61.cpp1.ii". make: [build/src/operator/tensor/broadcast_reduce_op_index_gpu.o] Error 2 1 error detected in the compilation of "/tmp/tmpxft_000033e0_00000000-17_elemwise_binary_scalar_op_basic.compute_61.cpp1.ii". make: [build/src/operator/tensor/elemwise_binary_scalar_op_basic_gpu.o] Error 2 1 error detected in the compilation of "/tmp/tmpxft_00003375_00000000-17_elemwise_binary_scalar_op_extended.compute_61.cpp1.ii". make: [build/src/operator/tensor/elemwise_binary_scalar_op_extended_gpu.o] Error 2 1 error detected in the compilation of "/tmp/tmpxft_00003379_00000000-17_elemwise_binary_broadcast_op_extended.compute_61.cpp1.ii". make: [build/src/operator/tensor/elemwise_binary_broadcast_op_extended_gpu.o] Error 2 1 error detected in the compilation of "/tmp/tmpxft_000033d5_00000000-17_elemwise_binary_broadcast_op_basic.compute_61.cpp1.ii". make: [build/src/operator/tensor/elemwise_binary_broadcast_op_basic_gpu.o] Error 2 1 error detected in the compilation of "/tmp/tmpxft_000033c3_00000000-17_broadcast_reduce_op_value.compute_61.cpp1.ii". make: [build/src/operator/tensor/broadcast_reduce_op_value_gpu.o] Error 2 1 error detected in the compilation of "/tmp/tmpxft_00003435_00000000-17_indexing_op.compute_61.cpp1.ii". 1 error detected in the compilation of "/tmp/tmpxft_0000340e_00000000-17_elemwise_unary_op.compute_61.cpp1.ii". make: [build/src/operator/tensor/indexing_op_gpu.o] Error 2 make: *** [build/src/operator/tensor/elemwise_unary_op_gpu.o] Error 2

I don't know what's wrong, could u please help me out. thanks a lot!

msracver / Deformable-ConvNets

MXNetError when I tried to run python ./rfcn/demo.py #43