Could not load dynamic library 'cudart64_110.dll' error

cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 

Could not load dynamic library 'cudart64_110.dll' error

3,743 Views
Priyanka23
Contributor II

I am trying to run eIq example flower_lab.py. using MacBook pro with windows installed.But i am getting the below error.

W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'cudart64_110.dll'; dlerror: cudart64_110.dll not found
2022-01-19 21:25:37.376518: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
2022-01-19 21:25:44.556092: E tensorflow/stream_executor/cuda/cuda_driver.cc:271] failed call to cuInit: CUDA_ERROR_UNKNOWN: unknown error
2022-01-19 21:25:44.572587: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:169] retrieving CUDA diagnostic information for host: DESKTOP-J9A442V
2022-01-19 21:25:44.575980: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:176] hostname: DESKTOP-J9A442V
2022-01-19 21:25:44.576776: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX AVX2
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
Traceback (most recent call last):
File "flower_lab.py", line 15, in <module>
mobilenetv1_spec = model_spec.ImageModelSpec(uri='https://tfhub.dev/google/imagenet/mobilenet_v1_025_128/feature_vector/4')
AttributeError: module 'tflite_model_maker.model_spec' has no attribute 'ImageModelSpec'.

Looking for suggestions and guidance in resolving this issue.

thanks

0 Kudos
Reply
1 Reply

3,731 Views
Zhiming_Liu
NXP TechSupport
NXP TechSupport

EIQ tool needs NVIDIA GPU that installed cuda and cudnn

0 Kudos
Reply