bi-att-flow icon indicating copy to clipboard operation
bi-att-flow copied to clipboard

Unreferenced variable error while running dev-demo

Open prathusha94 opened this issue 5 years ago • 0 comments

I'm trying to work with the branch dev-demo and following the exact same steps mentioned. Once I preprocess the data and run python -m basic.cli --mode train --noload --debug , I get the following error : File "/home/prat2/anaconda3/envs/tensorflow_gpuenv/lib/python3.6/runpy.py", line 193, in _run_module_as_main "__main__", mod_spec) File "/home/prat2/anaconda3/envs/tensorflow_gpuenv/lib/python3.6/runpy.py", line 85, in _run_code exec(code, run_globals) File "/home/prat2/demo/bi-att-flow/basic/cli.py", line 112, in <module> tf.app.run() File "/home/prat2/anaconda3/envs/tensorflow_gpuenv/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 48, in run _sys.exit(main(_sys.argv[:1] + flags_passthrough)) File "/home/prat2/demo/bi-att-flow/basic/cli.py", line 109, in main m(config) File "/home/prat2/demo/bi-att-flow/basic/main.py", line 24, in main _train(config) File "/home/prat2/demo/bi-att-flow/basic/main.py", line 67, in _train train_data = read_data(config, 'train', config.load, data_filter=data_filter) File "/home/prat2/demo/bi-att-flow/basic/read_data.py", line 176, in read_data mask.append(data_filter(each, shared)) UnboundLocalError: local variable 'shared' referenced before assignment I was able to successfully train the model using dev branch but getting the above error for "dev-demo" . I'm working with tensorflow 1.4

Would appreciate any help with this.

prathusha94 avatar Apr 04 '19 02:04 prathusha94