Code Monkey home page Code Monkey logo

rnn_tabletennis's People

Contributors

brotherjing avatar

Stargazers

avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar

Watchers

avatar avatar

Forkers

nuzhny007 mokoing chao-jiang yunfan-chen roozbehsanaei whitedragon6 xinchan aurelius-ai yanhao001 arslan1979

rnn_tabletennis's Issues

run time error python 3.6 


Traceback (most recent call last):
  File "main.py", line 146, in <module>
    tf.app.run(main=main)
  File "/Users/Moh/anaconda/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 124, in run
    _sys.exit(main(argv))
  File "main.py", line 101, in main
    model = Model(True, config)
  File "/Users/Moh/Desktop/thesiss/RNN_tabletennis-master/model.py", line 23, in __init__
    self.x = tf.placeholder(tf.float32, shape=[self.batch_size, self.coords, None], name='Input_data')
AttributeError: can't set attribute

What are train_perplexity and test_preplexity? 

train_perplexity = run_epoch(session, model, X_train, y_train, eval_op=model.train_op, n_epoch=i+1, summary=summary, summary_writer=summary_writer, verbose=True)
print "Epoch: %d train perplexity: %.3f"%(i+1, train_perplexity)

test_perplexity = run_epoch(session, mtest, X_test, y_test)
print "Epoch: %d test perplexity: %.3f"%(i+1, test_perplexity)

coord_30.csv usage

if I am using coord_30.csv data file , then the configuration is:
else: config['seq_len'] = 70#29 config['batch_size'] = 20 config['overlap_rate'] = 0.0 config['lr_decay'] = 0.9 config['max_epoch'] = 10 config['max_max_epoch'] = 15

Why config['seq_len'] = 70#29 ? shouldn't it be 30 ?

there is a run time error as well. Is the project working without any bugs ?

How are you feeding the data ?

A sequence represents a path. So are you feeding 1 path at time or a part of the path ?
Where is this mentioned in your code?

What is the expected output and the breakpoint?

After the training the model, are you predicting a trajectory or just classifying trajectories ?
If you are prediciting trjacetories then you are feeding only starting point and timestep and the output should be the whole trajectory. But there should be a goal point or a break point to tell our model where to stop, right ?

MDN

Why MDN ?

session.graph.get_tensor_by_name("Test/Model/zeros:0") 

placeholder_x = session.graph.get_tensor_by_name("Test/Model/Input_data:0")
initial_state_c_0 = session.graph.get_tensor_by_name("Test/Model/zeros:0")
initial_state_h_0 = session.graph.get_tensor_by_name("Test/Model/zeros_1:0")
initial_state_c_1 = session.graph.get_tensor_by_name("Test/Model/zeros_2:0")
initial_state_h_1 = session.graph.get_tensor_by_name("Test/Model/zeros_3:0")

KeyError: "The name 'Test/Model/zeros:0' refers to a Tensor which does not exist. The operation, 'Test/Model/zeros', does not exist in the graph."
Test/Model/zeros_1:0
Test/Model/zeros_2:0
Test/Model/zeros_3:0

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.