anirudh2290 commented on a change in pull request #15118: Conversion from FP32
model to Mixed Precision model
URL: https://github.com/apache/incubator-mxnet/pull/15118#discussion_r293000595
##########
File path: tests/python/tensorrt/test_tensorrt_lenet5.py
##########
@@ -46,7 +46,7 @@ def run_inference(sym, arg_params, aux_params, mnist,
all_test_labels, batch_siz
# Get this value from all_test_labels
# Also get classes from the dataset
num_ex = 10000
- all_preds = np.zeros([num_ex, 10])
+ all_preds = np.zeros([num_ex, 10], dtype=np.float32)
Review comment:
No it wont come from outputs
```
>>> x = np.zeros((2, 3))
>>> y = np.zeros((2, 3), dtype=np.float32)
>>> x[:] = y
>>> x
array([[ 0., 0., 0.],
[ 0., 0., 0.]])
>>> x.dtype
dtype('float64')
```
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
