Open smsalaken opened 5 years ago
I am trying to reproduce the output using example inference code for custom dataset. Followed the shown process to generate my_custom_dataset but the output does not match.
my_custom_dataset
Command: docker run -it --rm -vpwd:/decaNLP/ -u $(id -u):$(id -g) bmccann/decanlp:torch041 bash -c "python /decaNLP/predict.py --evaluate valid --path /decaNLP/squad_mqan_cove_cpu --checkpoint_name iteration_39000.pth --tasks my_custom_dataset --device -1"
docker run -it --rm -v
:/decaNLP/ -u $(id -u):$(id -g) bmccann/decanlp:torch041 bash -c "python /decaNLP/predict.py --evaluate valid --path /decaNLP/squad_mqan_cove_cpu --checkpoint_name iteration_39000.pth --tasks my_custom_dataset --device -1"
Here is the output I am getting, which does not show the prediction at all. It also keeps expanding the vocabulary everytime I run the above command.
39000 77.18 Arguments: {'best_checkpoint': '/decaNLP/squad_mqan_cove_cpu/iteration_39000.pth', 'bleu': False, 'checkpoint_name': 'iteration_39000.pth', 'cove': True, 'data': '/decaNLP/.data/', 'devices': [-1], 'dimension': 200, 'dropout_ratio': 0.0, 'embeddings': '/decaNLP/.embeddings', 'evaluate': 'valid', 'intermediate_cove': False, 'load': None, 'lower': True, 'max_generative_vocab': 50000, 'max_output_length': 100, 'max_val_context_length': 400, 'model': 'MultitaskQuestionAnsweringNetwork', 'overwrite_predictions': False, 'path': '/decaNLP/squad_mqan_cove_cpu', 'rnn_layers': 1, 'rouge': False, 'seed': 123, 'silent': False, 'task_to_metric': {'cnn_dailymail': 'avg_rouge', 'iwslt.en.de': 'bleu', 'multinli.in.out': 'em', 'schema': 'em', 'squad': 'nf1', 'srl': 'nf1', 'sst': 'em', 'wikisql': 'lfem', 'woz.en': 'joint_goal_em', 'zre': 'corpus_f1'}, 'tasks': ['my_custom_dataset'], 'transformer_heads': 3, 'transformer_hidden': 150, 'transformer_layers': 2, 'val_batch_size': [256]} Loading from /decaNLP/squad_mqan_cove_cpu/iteration_39000.pth Initializing Model Loading my_custom_dataset Caching data to /decaNLP/.data/my_custom_dataset/.cache/val.jsonl/None Vocabulary has 87176 tokens from training Vocabulary has expanded to 87176 tokens 100%|█████████████████████████████████████████████████████████████████████████████████████| 874474/874474 [00:30<00:00, 28815.11it/s]
I am running this on Macbook Pro with Anaconda. Here is the output for conda list:
conda list
# packages in environment at /Users/MY_USER_NAME/anaconda3: # # Name Version Build Channel _ipyw_jlab_nb_ext_conf 0.1.0 py36_0 alabaster 0.7.12 py36_0 anaconda 5.0.1 py36h6e48e2d_1 anaconda-client 1.7.2 py36_0 anaconda-navigator 1.9.2 py36_0 anaconda-project 0.8.2 py36_0 appnope 0.1.0 py36hf537a9a_0 appscript 1.0.1 py36h1de35cc_1 asn1crypto 0.24.0 py36_0 astroid 2.1.0 py36_0 astropy 3.0.5 py36h1de35cc_0 atomicwrites 1.2.1 py36_0 attrs 18.2.0 py36h28b3542_0 babel 2.6.0 py36_0 backcall 0.1.0 py36_0 backports 1.0 py36_1 backports.os 0.1.1 py36_0 backports.shutil_get_terminal_size 1.0.0 py36_2 beautifulsoup4 4.6.3 py36_0 bitarray 0.8.3 py36h1de35cc_0 bkcharts 0.2 py36h073222e_0 blas 1.0 mkl blaze 0.11.3 py36h02e7a37_0 bleach 3.0.2 py36_0 blosc 1.14.4 hd9629dc_0 bokeh 1.0.2 py36_0 boto 2.49.0 py36_0 bottleneck 1.2.1 py36h1d22016_1 bzip2 1.0.6 h1de35cc_5 ca-certificates 2019.1.23 0 certifi 2018.11.29 py36_0 cffi 1.11.5 py36h6174b99_1 chardet 3.0.4 py36_1 click 7.0 py36_0 cloudpickle 0.6.1 py36_0 clyent 1.2.2 py36_1 colorama 0.4.0 py36_0 conda 4.6.3 py36_0 conda-build 3.17.1 py36_0 conda-env 2.6.0 1 conda-verify 3.1.1 py36_0 contextlib2 0.5.5 py36hd66e5e7_0 cryptography 2.5 py36ha12b0ac_0 curl 7.63.0 ha441bb4_1000 cycler 0.10.0 py36hfc81398_0 cython 0.29 py36h0a44026_0 cytoolz 0.9.0.1 py36h1de35cc_1 dask 1.0.0 py36_0 dask-core 1.0.0 py36_0 datashape 0.5.4 py36_1 dbus 1.13.2 h760590f_1 decorator 4.3.0 py36_0 distributed 1.25.0 py36_0 docutils 0.14 py36hbfde631_0 entrypoints 0.2.3 py36_2 et_xmlfile 1.0.1 py36h1315bdc_0 expat 2.2.6 h0a44026_0 fastcache 1.0.2 py36h1de35cc_2 filelock 3.0.10 py36_0 flake8 3.6.0 py36_0 flask 1.0.2 py36_1 flask-cors 3.0.7 py36_0 freetype 2.9.1 hb4e5f40_0 future 0.17.1 py36_0 get_terminal_size 1.0.0 h7520d66_0 gettext 0.19.8.1 h15daf44_3 gevent 1.3.7 py36h1de35cc_1 glib 2.56.2 hd9629dc_0 glob2 0.6 py36_1 gmp 6.1.2 hb37e062_1 gmpy2 2.0.8 py36h6ef4df4_2 greenlet 0.4.15 py36h1de35cc_0 h5py 2.8.0 py36h878fce3_3 hdf5 1.10.2 hfa1e0ec_1 heapdict 1.0.0 py36_2 html5lib 1.0.1 py36_0 icu 58.2 h4b95b61_1 idna 2.7 py36_0 imageio 2.4.1 py36_0 imagesize 1.1.0 py36_0 importlib_metadata 0.6 py36_0 intel-openmp 2019.1 144 ipykernel 5.1.0 py36h39e3cac_0 ipython 7.2.0 py36h39e3cac_0 ipython_genutils 0.2.0 py36h241746c_0 ipywidgets 7.4.2 py36_0 isort 4.3.4 py36_0 itsdangerous 1.1.0 py36_0 jbig 2.1 h4d881f8_0 jdcal 1.4 py36_0 jedi 0.13.1 py36_0 jinja2 2.10 py36_0 jpeg 9b he5867d9_2 jsonschema 2.6.0 py36hb385e00_0 jupyter 1.0.0 py36_7 jupyter_client 5.2.3 py36_0 jupyter_console 6.0.0 py36_0 jupyter_core 4.4.0 py36_0 jupyterlab 0.35.3 py36_0 jupyterlab_launcher 0.13.1 py36_0 jupyterlab_server 0.2.0 py36_0 keyring 16.1.1 py36_0 kiwisolver 1.0.1 py36h0a44026_0 krb5 1.16.1 hddcf347_7 lazy-object-proxy 1.3.1 py36h1de35cc_2 libarchive 3.3.3 he8b1da1_2 libcurl 7.63.0 h051b688_1000 libcxx 4.0.1 hcfea43d_1 libcxxabi 4.0.1 hcfea43d_1 libedit 3.1.20170329 hb402a30_2 libffi 3.2.1 h475c297_4 libgfortran 3.0.1 h93005f0_2 libiconv 1.15 hdd342a3_7 liblief 0.9.0 h2a1bed3_0 libpng 1.6.35 ha441bb4_0 libsodium 1.0.16 h3efe00b_0 libssh2 1.8.0 ha12b0ac_4 libtiff 4.0.9 hcb84e12_2 libxml2 2.9.8 hab757c2_1 libxslt 1.1.32 hb819dd2_0 llvmlite 0.26.0 py36h8c7ce04_0 locket 0.2.0 py36hca03003_1 lxml 4.2.5 py36hef8c89e_0 lz4-c 1.8.1.2 h1de35cc_0 lzo 2.10 h362108e_2 markupsafe 1.1.0 py36h1de35cc_0 matplotlib 3.0.1 py36h54f8f79_0 mccabe 0.6.1 py36_1 mistune 0.8.4 py36h1de35cc_0 mkl 2018.0.3 1 mkl-service 1.1.2 py36h6b9c3cc_5 mkl_fft 1.0.6 py36hb8a8100_0 mkl_random 1.0.1 py36h5d10147_1 more-itertools 4.3.0 py36_0 mpc 1.1.0 h6ef4df4_1 mpfr 4.0.1 h3018a27_3 mpmath 1.0.0 py36_2 msgpack-python 0.5.6 py36h04f5b5a_1 multipledispatch 0.6.0 py36_0 navigator-updater 0.2.1 py36_0 nbconvert 5.3.1 py36_0 nbformat 4.4.0 py36h827af21_0 ncurses 6.1 h0a44026_1 networkx 2.2 py36_1 ninja 1.8.2 py36h04f5b5a_1 nltk 3.3.0 py36_0 nose 1.3.7 py36_2 notebook 5.7.2 py36_0 numba 0.35.0 np113py36_6 numexpr 2.6.8 py36h1dc9127_0 numpy 1.15.4 py36h6a91979_0 numpy-base 1.15.4 py36h8a80b8c_0 numpydoc 0.8.0 py36_0 odo 0.5.1 py36hc1af34a_0 olefile 0.46 py36_0 openpyxl 2.5.11 py36_0 openssl 1.1.1a h1de35cc_0 packaging 18.0 py36_0 pandas 0.23.4 py36h6440ff4_0 pandoc 2.2.3.2 0 pandocfilters 1.4.2 py36_1 parso 0.3.1 py36_0 partd 0.3.9 py36_0 path.py 11.5.0 py36_0 pathlib2 2.3.2 py36_0 patsy 0.5.1 py36_0 pcre 8.42 h378b8a2_0 pep8 1.7.1 py36_0 pexpect 4.6.0 py36_0 pickleshare 0.7.5 py36_0 pillow 5.3.0 py36hb68e598_0 pip 18.1 py36_0 pkginfo 1.4.2 py36_1 pluggy 0.8.0 py36_0 ply 3.11 py36_0 prometheus_client 0.4.2 py36_0 prompt_toolkit 2.0.7 py36_0 psutil 5.4.8 py36h1de35cc_0 ptyprocess 0.6.0 py36_0 py 1.7.0 py36_0 py-lief 0.9.0 py36hd4eaf27_0 pycodestyle 2.4.0 py36_0 pycosat 0.6.3 py36h1de35cc_0 pycparser 2.19 py36_0 pycrypto 2.6.1 py36h1de35cc_9 pycurl 7.43.0.2 py36ha12b0ac_0 pyflakes 2.0.0 py36_0 pygments 2.2.0 py36h240cd3f_0 pylint 2.2.2 py36_0 pyodbc 4.0.24 py36h0a44026_0 pyopenssl 18.0.0 py36_0 pyparsing 2.3.0 py36_0 pyqt 5.9.2 py36h655552a_2 pysocks 1.6.8 py36_0 pytables 3.4.4 py36h13cba08_0 pytest 4.0.1 py36_0 pytest-arraydiff 0.2 py36h39e3cac_0 pytest-astropy 0.4.0 py36_0 pytest-doctestplus 0.2.0 py36_0 pytest-openfiles 0.3.1 py36_0 pytest-remotedata 0.3.1 py36_0 python 3.6.7 haf84260_0 python-dateutil 2.7.5 py36_0 python-libarchive-c 2.8 py36_6 python.app 2 py36_9 pytorch 0.4.1 py36_cuda0.0_cudnn0.0_1 pytorch pytz 2018.7 py36_0 pywavelets 1.0.1 py36h1d22016_0 pyyaml 3.13 py36h1de35cc_0 pyzmq 17.1.2 py36h1de35cc_0 qt 5.9.6 h45cd832_2 qtawesome 0.5.3 py36_0 qtconsole 4.4.2 py36_0 qtpy 1.5.2 py36_0 readline 7.0 h1de35cc_5 requests 2.20.1 py36_0 rope 0.11.0 py36_0 ruamel_yaml 0.15.46 py36h1de35cc_0 scikit-image 0.14.0 py36h0a44026_1 scikit-learn 0.20.1 py36h4f467ca_0 scipy 1.1.0 py36h28f7352_1 seaborn 0.9.0 py36_0 send2trash 1.5.0 py36_0 setuptools 40.6.2 py36_0 simplegeneric 0.8.1 py36_2 singledispatch 3.4.0.3 py36hf20db9d_0 sip 4.19.8 py36h0a44026_0 six 1.11.0 py36_1 snappy 1.1.7 he62c110_3 snowballstemmer 1.2.1 py36h6c7b616_0 sortedcollections 1.0.1 py36_0 sortedcontainers 2.1.0 py36_0 sphinx 1.8.2 py36_0 sphinxcontrib 1.0 py36_1 sphinxcontrib-websupport 1.1.0 py36_1 spyder 3.3.2 py36_0 spyder-kernels 0.3.0 py36_0 sqlalchemy 1.2.14 py36h1de35cc_0 sqlite 3.25.3 ha441bb4_0 statsmodels 0.9.0 py36h1d22016_0 sympy 1.3 py36_0 tblib 1.3.2 py36hda67792_0 terminado 0.8.1 py36_1 testpath 0.4.2 py36_0 tk 8.6.8 ha441bb4_0 toolz 0.9.0 py36_0 torchvision 0.2.1 py36_1 pytorch tornado 5.1.1 py36h1de35cc_0 tqdm 4.28.1 py36h28b3542_0 traitlets 4.3.2 py36h65bd3ce_0 typed-ast 1.1.0 py36h1de35cc_0 typing 3.6.4 py36_0 unicodecsv 0.14.1 py36he531d66_0 unixodbc 2.3.7 h1de35cc_0 urllib3 1.23 py36_0 wcwidth 0.1.7 py36h8c6ec74_0 webencodings 0.5.1 py36_1 werkzeug 0.14.1 py36_0 wheel 0.32.3 py36_0 widgetsnbextension 3.4.2 py36_0 wrapt 1.10.11 py36h1de35cc_2 wurlitzer 1.0.2 py36_0 xlrd 1.1.0 py36_1 xlsxwriter 1.1.2 py36_0 xlwings 0.15.0 py36_0 xlwt 1.2.0 py36h5ad1178_0 xz 5.2.4 h1de35cc_4 yaml 0.1.7 hc338f04_2 zeromq 4.2.5 h0a44026_1 zict 0.1.3 py36_0 zlib 1.2.11 h1de35cc_3 zstd 1.3.3 h2a6be3a_0
I am trying to reproduce the output using example inference code for custom dataset. Followed the shown process to generate
my_custom_dataset
but the output does not match.Command:
docker run -it --rm -v
pwd:/decaNLP/ -u $(id -u):$(id -g) bmccann/decanlp:torch041 bash -c "python /decaNLP/predict.py --evaluate valid --path /decaNLP/squad_mqan_cove_cpu --checkpoint_name iteration_39000.pth --tasks my_custom_dataset --device -1"
Here is the output I am getting, which does not show the prediction at all. It also keeps expanding the vocabulary everytime I run the above command.
I am running this on Macbook Pro with Anaconda. Here is the output for
conda list
: