multivariate time series example

[mahmoodn]

For the multivariate time series example, I changed the default electricity.txt to exchange_rate.txt, however I get the following error

$ python lstnet.py --gpus=0 --batch-size=20 --num-filters=20 --num-epochs=1
lstnet.py:82: FutureWarning: Method .as_matrix will be removed in a future version. Use .values instead.
  x = feature_df.as_matrix()
[13:33:50] src/operator/nn/./cudnn/./cudnn_algoreg-inl.h:97: Running performance tests to find the best convolution algorithm, this can take a while... (setting env variable MXNET_CUDNN_AUTOTUNE_DEFAULT to 0 to disable)

Metrics: Epoch 1, Training {'RAE': 0.20321928, 'RSE': 0.19795567, 'CORR': 0.68863547}
Metrics: Epoch 1, Validation {'RAE': 0.21487446, 'RSE': 0.24589065, 'CORR': 0.49501655}
Traceback (most recent call last):
  File "lstnet.py", line 242, in <module>
    train(symbol, train_iter, val_iter, data_names, label_names)
  File "lstnet.py", line 216, in train
    module.save_checkpoint(prefix=os.path.join("../models/", args.model_prefix), epoch=epoch, save_optimizer_states=False)
  File "/home/mahmood/mx/mxnet/python/mxnet/module/module.py", line 178, in save_checkpoint
    self._symbol.save('%s-symbol.json'%prefix)
  File "/home/mahmood/mx/mxnet/python/mxnet/symbol/symbol.py", line 1216, in save
    check_call(_LIB.MXSymbolSaveToFile(self.handle, c_str(fname)))
  File "/home/mahmood/mx/mxnet/python/mxnet/base.py", line 252, in check_call
    raise MXNetError(py_str(_LIB.MXGetLastError()))
mxnet.base.MXNetError: [13:34:22] src/io/local_filesys.cc:199: Check failed: allow_null  LocalFileSystem::Open "../models/electricity_model-symbol.json": No such file or directory

Stack trace returned 10 entries:
[bt] (0) /home/mahmood/mx/mxnet/python/mxnet/../../lib/libmxnet.so(dmlc::StackTrace[abi:cxx11]()+0x169) [0x7f86df663659]
[bt] (1) /home/mahmood/mx/mxnet/python/mxnet/../../lib/libmxnet.so(dmlc::io::LocalFileSystem::Open(dmlc::io::URI const&, char const*, bool)+0x653) [0x7f86e29052e3]
[bt] (2) /home/mahmood/mx/mxnet/python/mxnet/../../lib/libmxnet.so(dmlc::Stream::Create(char const*, char const*, bool)+0x211) [0x7f86e28f74f1]
[bt] (3) /home/mahmood/mx/mxnet/python/mxnet/../../lib/libmxnet.so(MXSymbolSaveToFile+0x59) [0x7f86e27d2f99]
[bt] (4) /home/mahmood/anaconda3/lib/python3.7/lib-dynload/../../libffi.so.6(ffi_call_unix64+0x4c) [0x7f870096eec0]
[bt] (5) /home/mahmood/anaconda3/lib/python3.7/lib-dynload/../../libffi.so.6(ffi_call+0x22d) [0x7f870096e87d]
[bt] (6) /home/mahmood/anaconda3/lib/python3.7/lib-dynload/_ctypes.cpython-37m-x86_64-linux-gnu.so(_ctypes_callproc+0x2ce) [0x7f872b429eee]
[bt] (7) /home/mahmood/anaconda3/lib/python3.7/lib-dynload/_ctypes.cpython-37m-x86_64-linux-gnu.so(+0x13924) [0x7f872b42a924]
[bt] (8) python(_PyObject_FastCallKeywords+0x4ab) [0x559eff13265b]
[bt] (9) python(_PyEval_EvalFrameDefault+0x532e) [0x559eff18e40e]

What should I do?

[mxnet-label-bot]

Hey, this is the MXNet Label Bot. Thank you for submitting the issue! I will try and suggest some labels so that the appropriate MXNet community members can help resolve it. Here are my recommended labels: Example

[lanking520]

../models/electricity_model-symbol.json

The problems is model not found. Please either rename your model file name to this one or make change in the code to load your new model name.

[ThomasDelteil]

@mahmoodn, Please re-open if you are still working on the issue. Thanks!