search

una-dinosauria / 3d-pose-baseline

A simple baseline for 3d human pose estimation in tensorflow. Presented at ICCV 17.
MIT License
1.42k stars 354 forks source link

exception occurred #64

Closed postgraduater closed 5 years ago

postgraduater commented 6 years ago

exception occurred:

  1. Your operating system：win10
  2. Your tensorflow version：conda3
  3. Your python version：conda3
  4. The stack trace of the error that you see：

。。。 Working on epoch 1, batch 23900 / 24371... done in 8.22 ms Working on epoch 1, batch 24000 / 24371... done in 7.98 ms Working on epoch 1, batch 24100 / 24371... done in 8.02 ms Working on epoch 1, batch 24200 / 24371... done in 7.99 ms Working on epoch 1, batch 24300 / 24371... done in 8.09 ms

Global step: 24371 Learning rate: 9.90e-04 Train loss avg: 0.1856

===Action=== ==mm== Directions 61.55 Discussion 68.38 Eating 69.96 Greeting 71.66 Phoning 94.54 Photo 96.53 Posing 63.64 Purchases 68.17 Sitting 94.18 SittingDown 122.07 Smoking 78.02 Waiting 73.70 WalkDog 78.72 Walking 63.86 WalkTogether 67.49 Average 78.16

2018-06-04 09:47:31.501191: W C:\tf_jenkins\home\workspace\rel-win\M\windows-gpu\PY\36\tensorflow\core\framework\op_kernel.cc:1192] Not found: Failed to create a NewWriteableFile: experiments\All\dropout_0.5\epochs_1\lr_0.001\residual\depth_2\linear_size1024\batch_size_64\no_procrustes\maxnorm\batch_normalization\use_stacked_hourglass\predict_17\checkpoint-24371.data-00000-of-00001.tempstate15701499322097665914 : ; No such process Saving the model... Traceback (most recent call last): File "C:\Users\Zhang\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1323, in _do_call return fn(*args) File "C:\Users\Zhang\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1302, in _run_fn status, run_metadata) File "C:\Users\Zhang\Anaconda3\lib\site-packages\tensorflow\python\framework\errors_impl.py", line 473, in exit c_api.TF_GetCode(self.status.status)) tensorflow.python.framework.errors_impl.NotFoundError: Failed to create a NewWriteableFile: experiments\All\dropout_0.5\epochs_1\lr_0.001\residual\depth_2\linear_size1024\batch_size_64\no_procrustes\maxnorm\batch_normalization\use_stacked_hourglass\predict_17\checkpoint-24371.data-00000-of-00001.tempstate15701499322097665914 : ϵͳ\udcd5Ҳ\udcbb\udcb5\udcbdָ\udcb6\udca8\udcb5\udcc4·\udcbe\udcb6\udca1\udca3 ; No such process [[Node: save/SaveV2 = SaveV2[dtypes=[DT_FLOAT, DT_FLOAT, DT_INT32, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/SaveV2/tensor_names, save/SaveV2/shape_and_slices, beta1_power/_169, beta2_power/_171, global_step, learning_rate/_173, linear_model/b1/_175, linear_model/b1/Adam/_177, linear_model/b1/Adam_1/_179, linear_model/b4/_181, linear_model/b4/Adam/_183, linear_model/b4/Adam_1/_185, linear_model/batch_normalization/beta/_187, linear_model/batch_normalization/beta/Adam/_189, linear_model/batch_normalization/beta/Adam_1/_191, linear_model/batch_normalization/gamma/_193, linear_model/batch_normalization/gamma/Adam/_195, linear_model/batch_normalization/gamma/Adam_1/_197, linear_model/batch_normalization/moving_mean/_199, linear_model/batch_normalization/moving_variance/_201, linear_model/two_linear_0/b2_0/_203, linear_model/two_linear_0/b2_0/Adam/_205, linear_model/two_linear_0/b2_0/Adam_1/_207, linear_model/two_linear_0/b3_0/_209, linear_model/two_linear_0/b3_0/Adam/_211, linear_model/two_linear_0/b3_0/Adam_1/_213, linear_model/two_linear_0/batch_normalization10/beta/_215, linear_model/two_linear_0/batch_normalization10/beta/Adam/_217, linear_model/two_linear_0/batch_normalization10/beta/Adam_1/_219, linear_model/two_linear_0/batch_normalization10/gamma/_221, linear_model/two_linear_0/batch_normalization10/gamma/Adam/_223, linear_model/two_linear_0/batch_normalization10/gamma/Adam_1/_225, linear_model/two_linear_0/batch_normalization10/moving_mean/_227, linear_model/two_linear_0/batch_normalization10/moving_variance/_229, linear_model/two_linear_0/batch_normalization20/beta/_231, linear_model/two_linear_0/batch_normalization20/beta/Adam/_233, linear_model/two_linear_0/batch_normalization20/beta/Adam_1/_235, linear_model/two_linear_0/batch_normalization20/gamma/_237, linear_model/two_linear_0/batch_normalization20/gamma/Adam/_239, linear_model/two_linear_0/batch_normalization20/gamma/Adam_1/_241, linear_model/two_linear_0/batch_normalization20/moving_mean/_243, linear_model/two_linear_0/batch_normalization20/moving_variance/_245, linear_model/two_linear_0/w2_0/_247, linear_model/two_linear_0/w2_0/Adam/_249, linear_model/two_linear_0/w2_0/Adam_1/_251, linear_model/two_linear_0/w3_0/_253, linear_model/two_linear_0/w3_0/Adam/_255, linear_model/two_linear_0/w3_0/Adam_1/_257, linear_model/two_linear_1/b2_1/_259, linear_model/two_linear_1/b2_1/Adam/_261, linear_model/two_linear_1/b2_1/Adam_1/_263, linear_model/two_linear_1/b3_1/_265, linear_model/two_linear_1/b3_1/Adam/_267, linear_model/two_linear_1/b3_1/Adam_1/_269, linear_model/two_linear_1/batch_normalization11/beta/_271, linear_model/two_linear_1/batch_normalization11/beta/Adam/_273, linear_model/two_linear_1/batch_normalization11/beta/Adam_1/_275, linear_model/two_linear_1/batch_normalization11/gamma/_277, linear_model/two_linear_1/batch_normalization11/gamma/Adam/_279, linear_model/two_linear_1/batch_normalization11/gamma/Adam_1/_281, linear_model/two_linear_1/batch_normalization11/moving_mean/_283, linear_model/two_linear_1/batch_normalization11/moving_variance/_285, linear_model/two_linear_1/batch_normalization21/beta/_287, linear_model/two_linear_1/batch_normalization21/beta/Adam/_289, linear_model/two_linear_1/batch_normalization21/beta/Adam_1/_291, linear_model/two_linear_1/batch_normalization21/gamma/_293, linear_model/two_linear_1/batch_normalization21/gamma/Adam/_295, linear_model/two_linear_1/batch_normalization21/gamma/Adam_1/_297, linear_model/two_linear_1/batch_normalization21/moving_mean/_299, linear_model/two_linear_1/batch_normalization21/moving_variance/_301, linear_model/two_linear_1/w2_1/_303, linear_model/two_linear_1/w2_1/Adam/_305, linear_model/two_linear_1/w2_1/Adam_1/_307, linear_model/two_linear_1/w3_1/_309, linear_model/two_linear_1/w3_1/Adam/_311, linear_model/two_linear_1/w3_1/Adam_1/_313, linear_model/w1/_315, linear_model/w1/Adam/_317, linear_model/w1/Adam_1/_319, linear_model/w4/_321, linear_model/w4/Adam/_323, linear_model/w4/Adam_1/_325)]]

una-dinosauria commented 6 years ago

Hi!

Try creating the folder experiments\All\dropout_0.5\epochs_1\lr_0.001\residual\depth_2\linear_size1024\batch_size_64\no_procrustes\maxnorm\batch_normalization\use_stacked_hourglass\predict_17\

Cheers,

una-dinosauria commented 6 years ago

More generally, consider changing this line

https://github.com/una-dinosauria/3d-pose-baseline/blob/f4606662ba4017dd1963147b44ce32dd5fb0c004/src/predict_3dpose.py#L83

To create a directory in windows with that path.

postgraduater commented 6 years ago

the folder experiments\All\dropout_0.5\epochs_1\lr_0.001\residual\depth_2\linear_size1024\batch_size_64\no_procrustes\maxnorm\batch_normalization\use_stacked_hourglass\predict_17\ already exists. But the same problem persists.

una-dinosauria commented 6 years ago

:thinking: no idea. According to https://stackoverflow.com/questions/45076911/tensorflow-failed-to-create-a-newwriteablefile-when-retraining-inception you may have to specify all the paths as absolute, not relative in Windows.

Another option is to move to Linux -- It works out of the box and it's free.

zkyf commented 6 years ago

Got the same problem. Solved by shortening the train_dir to: train_dir = os.path.join( FLAGS.train_dir, FLAGS.action) This is strange. Guess the original path exceeds a string length limits somewhere in windows edition of tf and the path is cut in the middle.

una-dinosauria commented 5 years ago

Closing for lack of activity. Please reopen if the issue is still ongoing.