Showing results for

- Intel Community
- Software Development SDKs and Libraries
- Intel® Distribution of OpenVINO™ Toolkit
- Movidius and tensorflow outputs dont match

- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Mute
- Printer Friendly Page

Highlighted
##

idata

Community Manager

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

12-26-2017
11:31 AM

240 Views

Movidius and tensorflow outputs dont match

Hi!

I've build a tensorflow model consisting of two convolutional and two fully connected layers. Then I initialize it with random variables, evaluate it on a np.ones vector and save the model.

```
input = tf.placeholder("float16", [1, 1604,9,1], name="x")
output = fc_gest(conv(input)) #output from my model
print(output)
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
saver = tf.train.Saver(tf.global_variables())
inp = np.ones((1,1604,9,1),dtype ="float16")
print('eval: ',np.float16(output.eval({input:inp})))
saver.save(sess, "./saved_sess/model.ckpts")
```

this code gives me ''add_3' as the name of my output vector and [[ 3.90820312 5.2890625 6.06640625 3.36328125 -4.046875

-6.26171875 10.546875 ]] a result of passing np.ones to my model.

I then generate a graph file with the command mvNCCompile model.ckpts.meta -in=x -on=add_3

After I get the graph file I load it to the stick and pass the same np.ones vector:

```
print("allocating graph")
graph = device.AllocateGraph(graphfile)
print("loading tensor")
inp = np.ones(([1,1604,9,1]),dtype ="float16")
graph.LoadTensor(inp, 'x')
print("computing result")
output, userobj = graph.GetResult()
print(np.float16(output))
print(output.shape)
```

the output of this is

allocating graph

loading tensor

computing result

[ nan nan nan nan nan nan nan]

(7,)

This time it's just nan's. If I make the model smaller it outputs numbers but they still don't match the TF output.

WHY?

2 Replies

Highlighted
##

@grisha In order to help debug your problem, I'd like to reproduce the issue you faced. If you could provide a link to the script you used in this post, it would save me a lot of time. Thanks.

idata

Community Manager

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

01-03-2018
07:49 PM

18 Views

Highlighted
##

@Tome_at_Intel I have partially solved the problem. I had to exclude addition operation from my graph and reshape it to be a square with three channels.

idata

Community Manager

- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Email to a Friend
- Report Inappropriate Content

01-17-2018
04:33 PM

18 Views

For more complete information about compiler optimizations, see our Optimization Notice.