UPGRADE YOUR BROWSER

We have detected your current browser version is not the latest one. Xilinx.com uses the latest web technologies to bring you the best online experience possible. Please upgrade to a Xilinx.com supported browser:Chrome, Firefox, Internet Explorer 11, Safari. Thank you!

cancel
Showing results for 
Search instead for 
Did you mean: 
Visitor lihahagang
Visitor
178 Views
Registered: ‎08-26-2019

An error in decent_q

Hi! I met an error in decent_q. When I decent a mobilenet v2 model, there is the question with:

 InvalidArgumentError (see above for traceback): Input to reshape is a tensor with 7526400 values, but the requested shape requires a multiple of 519168
  [[node Reshape (defined at /home/aaahhh/anaconda2/envs/decent/lib/python2.7/site-packages/tensorflow/contrib/decent_q/python/decent_q.py:130)  = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/device:CPU:0"](div, Reshape/shape)]]

Is there any restriction of the model or the input? And whether the preprocessing differs from different models? And what's the meaning of the input_fn?

Thanks! 

0 Kudos