-
Star
(152)
You must be signed in to star a gist -
Fork
(49)
You must be signed in to fork a gist
-
-
Save martinwicke/6838c23abdc53e6bcda36ed9f40cff39 to your computer and use it in GitHub Desktop.
same as seanmb on windows cpu on the dnnregressor.fit(input_fn=training_input_fn, steps=10000)
In the talk, Martin mentioned that the code was written for Tensorflow 1.2, and wouldn't work with earlier versions. So my guess is that you may be using an earlier version...
I have the same problem. I am sure I have tensorflow 1.2
I am new to ML and I miss on every tutorial, even this one, example how to use it. How can I manually input new car's params and get estimated output?
same issue
the error has already been fixed in source
tensorflow/tensorflow@5c1949e
@seanmb I had a similar issue when I was using a numeric column and accidentally had the shape parameter set. In your case it looks like body_style is set to an int64 (which is the 64 in the error) but you are specifying something like tf.feature_column.numeric_column('body-style',5). Drop the 5 and it should resolve this error.
Hi, thanks for article. can you please help me understand how to use that model? simple code sample? many thanks.
if I don't have jupiter notebook (in my case I work in Azure and have no graphics), can I put all the lines of code in one text file and run through it? How?
if I don't have jupiter notebook (in my case I work in Azure and have no graphics), can I put all the lines of code in one text file and run through it? How?
Try using Google CoLab, its free online Jupyter Notebook
I have put the code in one file called code.py which I pass as input to python(3). The job terminates without any output, but with the following messages. Anything I can do to fix?
WARNING:tensorflow:Using temporary folder as model directory: /home/u23885/tmp/tmpzouq5h7f
WARNING:tensorflow:RunConfig.uid (from tensorflow.contrib.learn.python.learn.estimators.run_config) is experimental and may change or be removed at any time, and without warning.
WARNING:tensorflow:RunConfig.uid (from tensorflow.contrib.learn.python.learn.estimators.run_config) is experimental and may change or be removed at any time, and without warning.
WARNING:tensorflow:From /home/u23885/.local/lib/python3.6/site-packages/tensorflow/contrib/learn/python/learn/monitors.py:267: BaseMonitor.init (from tensorflow.contrib.learn.python.learn.monitors) is deprecated and will be removed after 2016-12-05.
Instructions for updating:
Monitors are deprecated. Please use tf.train.SessionRunHook.
Hi, the dnnregressor is not working for me. I get the following error: ValueError:
Dimension size must be evenly divisible by 5 but is 64 for 'dnn/input_from_feature_columns/input_layer/body-style_indicator/Reshape' (op: 'Reshape') with input shapes: [64], [2] and with input tensors computed as partial shapes: input[1] = [?,5].