1-Introduction运行问题

[zeldarxf]

---------------------------------------------------------------------------EnforceNotMet Traceback (most recent call last) in 111 feed_dict['node_label'] = label 112 --> 113 train_loss = exe.run(fluid.default_main_program(), feed=feed_dict, fetch_list=[loss], return_numpy=True) 114 print('Epoch %d | Loss: %f'%(epoch, train_loss[0])) 115 print('1') /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/executor.py in run(self, program, feed, fetch_list, feed_var_name, fetch_var_name, scope, return_numpy, use_program_cache) 649 scope=scope, 650 return_numpy=return_numpy, --> 651 use_program_cache=use_program_cache) 652 else: 653 if fetch_list and program._is_data_parallel and program._program and ( /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/executor.py in _run(self, program, exe, feed, fetch_list, feed_var_name, fetch_var_name, scope, return_numpy, use_program_cache) 747 self._feed_data(program, feed, feed_var_name, scope) 748 if not use_program_cache: --> 749 exe.run(program.desc, scope, 0, True, True, fetch_var_name) 750 else: 751 exe.run_cached_prepared_ctx(ctx, scope, False, False, False) EnforceNotMet: Invoke operator sigmoid_cross_entropy_with_logits error.

[Liwb5]

Would you tell me your Paddle version and PGL version? I can run normally with Paddle==1.6 and PGL=1.0 .