deependersingla / deep_trader

This project uses reinforcement learning on stock market and agent tries to learn trading. The goal is to check if the agent can learn to read tape. The project is dedicated to hero in life great Jesse Livermore.
1.46k stars 504 forks source link

Could not find old network weights #3

Closed aaronzhudp closed 8 years ago

aaronzhudp commented 8 years ago

Could not find old network weights 0 Traceback (most recent call last): File "dqn_model.py", line 251, in main() File "dqn_model.py", line 183, in main agent.perceive(state,action,reward,next_state,done) File "dqn_model.py", line 91, in perceive self.train_Q_network() File "dqn_model.py", line 128, in train_Q_network self.saver.save(self.session, 'saved_networks/' + 'network' + '-dqn', global_step = self.time_step) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/saver.py", line 1037, in save {self.saver_def.filename_tensor_name: checkpoint_file}) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 340, in run run_metadata_ptr) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 564, in _run feed_dict_string, options, run_metadata) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 637, in _do_run target_list, options, run_metadata) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 659, in _do_call e.code) tensorflow.python.framework.errors.NotFoundError: saved_networks/network-dqn-3000.tempstate1294467586467070884 [[Node: save/save = SaveSlices[T=[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/cpu:0"](_recv_save/Const_0, save/save/tensor_names, save/save/shapes_and_slices, Variable, Variable/Adam, Variable/Adam_1, Variable_1, Variable_1/Adam, Variable_1/Adam_1, Variable_2, Variable_2/Adam, Variable_2/Adam_1, Variable_3, Variable_3/Adam, Variable_3/Adam_1, beta1_power, beta2_power)]] Caused by op u'save/save', defined at: File "dqn_model.py", line 251, in main() File "dqn_model.py", line 167, in main agent = DQN(data_dictionary) File "dqn_model.py", line 41, in init self.saver = tf.train.Saver() File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/saver.py", line 832, in init restore_sequentially=restore_sequentially) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/saver.py", line 500, in build save_tensor = self._AddSaveOps(filename_tensor, vars_to_save) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/saver.py", line 197, in _AddSaveOps save = self.save_op(filename_tensor, vars_to_save) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/saver.py", line 149, in save_op tensor_slices=[vs.slice_spec for vs in vars_to_save]) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/io_ops.py", line 172, in _save tensors, name=name) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_io_ops.py", line 341, in _save_slices name=name) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/op_def_library.py", line 661, in apply_op op_def=op_def) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2154, in create_op original_op=self._default_original_op, op_def=op_def) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1154, in init self._traceback = _extract_stack()

deependersingla commented 8 years ago

Hey,

Did you made directory saved_networks inside tensor-reinforcement? If not make it and run again.

Steps: a) cd tensor-reinforcement b) Copy data from https://drive.google.com/file/d/0B6ZrYxEMNGR-MEd5Ti0tTEJjMTQ/view into tensor-reinforcement directory and https://drive.google.com/file/d/0B6ZrYxEMNGR-Q0YwWWVpVnJ3YmM/view?usp=sharing into tensor-reinforcement. b) Create a directory saved_networks inside tensor_reinforcement for saving networks. c) python dqn_model.py

aaronzhudp commented 8 years ago

thanks! It is working now. it is inside a VM ubuntu system, kind of slow...

deependersingla commented 8 years ago

Are you using GPU?

aaronzhudp commented 8 years ago

No. Only CPU

aaronzhudp commented 8 years ago

i am going to do the same for Chinese Stock Market