sungwonida
commented
6 years ago Try Python 3 (maybe 3.5+ if not 3.0). Please refer to my requirements below. (Use tensorflow-gpu if you want) And I definitely recommand using virtualenv or conda for sandboxing the environments if you don't want to mess the things.
absl-py==0.2.2 astor==0.7.1 backcall==0.1.0 configobj==5.0.6 cycler==0.10.0 decorator==4.3.0 gast==0.2.0 grpcio==1.13.0 h5py==2.8.0 ipykernel==4.8.2 ipython==6.4.0 ipython-genutils==0.2.0 jedi==0.12.1 jupyter-client==5.2.3 jupyter-core==4.4.0 Keras==2.2.0 Keras-Applications==1.0.2 Keras-Preprocessing==1.0.1 kiwisolver==1.0.1 Markdown==2.6.11 matplotlib==2.2.2 numpy==1.14.5 opencv-python==3.4.1.15 pandas==0.23.3 parso==0.3.1 pexpect==4.6.0 pickleshare==0.7.4 Pillow==5.2.0 prompt-toolkit==1.0.15 protobuf==3.6.0 ptyprocess==0.6.0 pyarrow==0.9.0 pycocotools==2.0.0 Pygments==2.2.0 pyparsing==2.2.0 python-dateutil==2.7.3 pytz==2018.5 PyYAML==3.13 pyzmq==17.1.0 scipy==1.1.0 simplegeneric==0.8.1 six==1.11.0 tabulate==0.8.2 tensorboard==1.9.0 tensorflow==1.9.0 tensorpack==0.8.6 termcolor==1.1.0 tornado==5.1 tqdm==4.23.4 traitlets==4.3.2 wcwidth==0.1.7 Werkzeug==0.14.1
Hi, i'm poor at programming
so, i need some help please
i tried train_pose.py. but, it stoped at first epoch.
i ' don't know the reason. below is my terminal screen.
ubuntu 18 / python2.7 please help me
(tensorflow) sh@sh-WA50SCQ:~/Download/keras_Realtime_Multi-Person_Pose_Estimation-master$ python training/train_pose.py /home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/pandas/_libs/init.py:4: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88 from .tslib import iNaT, NaT, Timestamp, Timedelta, OutOfBoundsDatetime /home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/pandas/init.py:26: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88 from pandas._libs import (hashtable as _hashtable, /home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/pandas/core/dtypes/common.py:6: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88 from pandas._libs import algos, lib /home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/pandas/core/util/hashing.py:7: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88 from pandas._libs import hashing, tslib /home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/pandas/core/indexes/base.py:7: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88 from pandas._libs import (lib, index as libindex, tslib as libts, /home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/pandas/tseries/offsets.py:21: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88 import pandas._libs.tslibs.offsets as liboffsets /home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/pandas/core/ops.py:16: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88 from pandas._libs import algos as libalgos, ops as libops /home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/pandas/core/indexes/interval.py:32: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88 from pandas._libs.interval import ( /home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/pandas/core/internals.py:14: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88 from pandas._libs import internals as libinternals /home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/pandas/core/sparse/array.py:33: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88 import pandas._libs.sparse as splib /home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/pandas/core/window.py:36: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88 import pandas._libs.window as _window /home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/pandas/core/groupby/groupby.py:68: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88 from pandas._libs import (lib, reduction, /home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/pandas/core/reshape/reshape.py:30: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88 from pandas._libs import algos as _algos, reshape as _reshape /home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/pandas/io/parsers.py:45: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88 import pandas._libs.parsers as parsers /home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/pandas/io/pytables.py:50: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88 from pandas._libs import algos, lib, writers as libwriters /home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/h5py/init.py:36: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88 from ._conv import register_converters as _register_converters /home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/h5py/init.py:45: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88 from . import h5a, h5d, h5ds, h5f, h5fd, h5g, h5r, h5s, h5t, h5p, h5z /home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/h5py/_hl/group.py:22: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88 from .. import h5g, h5i, h5o, h5r, h5t, h5l, h5p Using TensorFlow backend.
/home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/scipy/sparse/lil.py:19: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88 from . import _csparsetools /home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/scipy/sparse/csgraph/init.py:165: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88 from ._shortest_path import shortest_path, floyd_warshall, dijkstra,\ /home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/scipy/sparse/csgraph/_validation.py:5: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88 from ._tools import csgraph_to_dense, csgraph_from_dense,\ /home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/scipy/sparse/csgraph/init.py:167: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88 from ._traversal import breadth_first_order, depth_first_order, \ /home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/scipy/sparse/csgraph/init.py:169: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88 from ._min_spanning_tree import minimum_spanning_tree /home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/scipy/sparse/csgraph/init.py:170: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88 from ._reordering import reverse_cuthill_mckee, maximum_bipartite_matching, \ /home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/scipy/linalg/basic.py:17: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88 from ._solve_toeplitz import levinson /home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/scipy/linalg/init.py:207: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88 from ._decomp_update import /home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/scipy/special/init.py:640: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88 from ._ufuncs import /home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/scipy/special/_ellip_harm.py:7: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88 from ._ellip_harm_2 import _ellipsoid, _ellipsoid_norm /home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/scipy/interpolate/_bsplines.py:10: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88 from . import _bspl /home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/scipy/spatial/init.py:95: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88 from .ckdtree import /home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/scipy/spatial/init.py:96: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88 from .qhull import /home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/scipy/spatial/_spherical_voronoi.py:18: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88 from . import _voronoi /home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/scipy/spatial/distance.py:122: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88 from . import _hausdorff /home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/scipy/ndimage/measurements.py:36: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88 from . import _ni_label Loading vgg19 weights... 2018-08-15 22:56:35.701104: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA 2018-08-15 22:56:35.751795: I tensorflow/core/common_runtime/process_util.cc:69] Creating new thread pool with default inter op setting: 2. Tune using inter_op_parallelism_threads for best performance.
Loaded VGG19 layer: block1_conv1 Loaded VGG19 layer: block1_conv2 Loaded VGG19 layer: block2_conv1 Loaded VGG19 layer: block2_conv2 Loaded VGG19 layer: block3_conv1 Loaded VGG19 layer: block3_conv2 Loaded VGG19 layer: block3_conv3 Loaded VGG19 layer: block3_conv4 Loaded VGG19 layer: block4_conv1 Loaded VGG19 layer: block4_conv2 loading annotations into memory... Done (t=10.77s) creating index... index created! Loading image annot 0/118287 Loading image annot 5000/118287 Loading image annot 7000/118287 Loading image annot 8000/118287 Loading image annot 14000/118287 Loading image annot 15000/118287 Loading image annot 17000/118287 Loading image annot 19000/118287 Loading image annot 21000/118287 Loading image annot 23000/118287 Loading image annot 24000/118287 Loading image annot 25000/118287 Loading image annot 28000/118287 Loading image annot 31000/118287 Loading image annot 33000/118287 Loading image annot 35000/118287 Loading image annot 36000/118287 Loading image annot 38000/118287 Loading image annot 39000/118287 Loading image annot 40000/118287 Loading image annot 41000/118287 Loading image annot 42000/118287 Loading image annot 43000/118287 Loading image annot 47000/118287 Loading image annot 52000/118287 Loading image annot 53000/118287 Loading image annot 55000/118287 Loading image annot 56000/118287 Loading image annot 58000/118287 Loading image annot 60000/118287 Loading image annot 61000/118287 Loading image annot 64000/118287 Loading image annot 65000/118287 Loading image annot 68000/118287 Loading image annot 71000/118287 Loading image annot 72000/118287 Loading image annot 73000/118287 Loading image annot 78000/118287 Loading image annot 79000/118287 Loading image annot 82000/118287 Loading image annot 85000/118287 Loading image annot 88000/118287 Loading image annot 91000/118287 Loading image annot 92000/118287 Loading image annot 97000/118287 Loading image annot 103000/118287 Loading image annot 106000/118287 Loading image annot 108000/118287 Loading image annot 110000/118287 Loading image annot 111000/118287 Loading image annot 113000/118287 Loading image annot 114000/118287 Loading image annot 115000/118287 Loading image annot 117000/118287 [0815 22:57:17 @parallel.py:291] [PrefetchDataZMQ] Will fork a dataflow more than one times. This assumes the datapoints are i.i.d.
Process _Worker-1: Traceback (most recent call last): File "/home/sh/.conda/envs/tensorflow/lib/python2.7/multiprocessing/process.py", line 267, in _bootstrap self.run() File "/home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/tensorpack/dataflow/parallel.py", line 267, in run for dp in self.ds.get_data(): File "/home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/tensorpack/dataflow/common.py", line 274, in get_data for dp in self.ds.get_data(): File "/home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/tensorpack/dataflow/common.py", line 274, in get_data for dp in self.ds.get_data(): File "/home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/tensorpack/dataflow/common.py", line 275, in get_data ret = self.func(copy(dp)) # shallow copy the list File "training/../training/dataset.py", line 96, in augment scale=meta.scale)) File "/home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/tensorpack/dataflow/imgaug/base.py", line 48, in augment_return_params return self._augment_return_params(d) File "/home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/tensorpack/dataflow/imgaug/base.py", line 54, in _augment_return_params prms = self._get_augment_params(d) File "training/../training/augmentors.py", line 226, in _get_augment_params scale_abs = self.target_dist / scale ZeroDivisionError: float division by zero
Process _Worker-3: Traceback (most recent call last): File "/home/sh/.conda/envs/tensorflow/lib/python2.7/multiprocessing/process.py", line 267, in _bootstrap self.run() File "/home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/tensorpack/dataflow/parallel.py", line 267, in run for dp in self.ds.get_data(): File "/home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/tensorpack/dataflow/common.py", line 274, in get_data for dp in self.ds.get_data(): File "/home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/tensorpack/dataflow/common.py", line 274, in get_data for dp in self.ds.get_data(): File "/home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/tensorpack/dataflow/common.py", line 275, in get_data ret = self.func(copy(dp)) # shallow copy the list File "training/../training/dataset.py", line 96, in augment scale=meta.scale)) File "/home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/tensorpack/dataflow/imgaug/base.py", line 48, in augment_return_params return self._augment_return_params(d) File "/home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/tensorpack/dataflow/imgaug/base.py", line 54, in _augment_return_params prms = self._get_augment_params(d) File "training/../training/augmentors.py", line 226, in _get_augment_params scale_abs = self.target_dist / scale ZeroDivisionError: float division by zero
Epoch 1/200000
2018-08-15 22:58:28.281299: W tensorflow/core/framework/op_kernel.cc:1318] OP_REQUIRES failed at mkl_concat_op.cc:816 : Aborted: Operation received an exception:Status: 3, message: could not create a reorder primitive descriptor, in file tensorflow/core/kernels/mkl_concat_op.cc:813
Traceback (most recent call last): File "training/train_pose.py", line 237, in
initial_epoch=last_epoch)
File "/home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/keras/legacy/interfaces.py", line 91, in wrapper
return func(*args, *kwargs)
File "/home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/keras/engine/training.py", line 1415, in fit_generator
initial_epoch=initial_epoch)
File "/home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/keras/engine/training_generator.py", line 213, in fit_generator
class_weight=class_weight)
File "/home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/keras/engine/training.py", line 1215, in train_on_batch
outputs = self.train_function(ins)
File "/home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/keras/backend/tensorflow_backend.py", line 2666, in call
return self._call(inputs)
File "/home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/keras/backend/tensorflow_backend.py", line 2636, in _call
fetched = self._callable_fn(array_vals)
File "/home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1454, in call
self._session._session, self._handle, args, status, None)
File "/home/sh/.conda/envs/tensorflow/lib/python2.7/site-packages/tensorflow/python/framework/errors_impl.py", line 519, in exit
c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.AbortedError: Operation received an exception:Status: 3, message: could not create a reorder primitive descriptor, in file tensorflow/core/kernels/mkl_concat_op.cc:813
[[Node: concatenate_1/concat = _MklConcatV2[N=3, T=DT_FLOAT, Tidx=DT_INT32, _kernel="MklOp", _device="/job:localhost/replica:0/task:0/device:CPU:0"](Mconv5_stage1_L1/BiasAdd, Mconv5_stage1_L2/BiasAdd, activation_12/Relu, training/MultiSGD/gradients/concatenate_1/concat_grad/mod, Mconv5_stage1_L1/BiasAdd:2, Mconv5_stage1_L2/BiasAdd:2, activation_12/Relu:1, DMT/_45)]]
PrefetchDataZMQ successfully cleaned-up.
PrefetchDataZMQ successfully cleaned-up.