I am using example "inception_v3" in tensorflow format:
When I try to run below command: python ./models/inception_v3/scripts/setup_inceptionv3.py -a ./temp-assets-cache -d
I get below error:
Traceback (most recent call last):
File "/home/vivek/snpe-sdk/snpe-1.2.2/models/inception_v3/scripts/create_inceptionv3_raws.py", line 124, in <module>
exit(main())
File "/home/vivek/snpe-sdk/snpe-1.2.2/models/inception_v3/scripts/create_inceptionv3_raws.py", line 121, in main
convert_img(src,dest,size)
File "/home/vivek/snpe-sdk/snpe-1.2.2/models/inception_v3/scripts/create_inceptionv3_raws.py", line 106, in convert_img
__create_raw_incv3(src_image,mean_rgb,128,False,False)
File "/home/vivek/snpe-sdk/snpe-1.2.2/models/inception_v3/scripts/create_inceptionv3_raws.py", line 44, in __create_raw_incv3
img_raw = __get_img_raw(img_filepath)
File "/home/vivek/snpe-sdk/snpe-1.2.2/models/inception_v3/scripts/create_inceptionv3_raws.py", line 14, in __get_img_raw
img = Image.open(img_filepath)
File "/usr/lib/python2.7/dist-packages/PIL/Image.py", line 2028, in open
raise IOError("cannot identify image file")
IOError: cannot identify image file
NFO: Creating inception_v3_quantized.dlc quantized model
[INFO] InitializeStderr: DebugLog initialized.
[INFO] Reading DLC: /home/vivek/snpe-sdk/snpe-1.2.2/models/inception_v3/dlc/inception_v3.dlc
[ERROR] DLC file /home/vivek/snpe-sdk/snpe-1.2.2/models/inception_v3/dlc/inception_v3.dlc doesn't exist!
[INFO] DebugLog shutting down.
INFO: Setup inception_v3 completed.
I have followed all the steps in installation. Please let me know I am missing anything.
Thanks,
Vivek
Hi Vivek,
This appears to be environment set up issue. Are you on Ubuntu 14.04? Did all environment setup steps at https://developer.qualcomm.com/software/snapdragon-neural-processing-eng... Setup the SDK complete successfully? Particularly python dependencies.
Thanks
Hi Moljaca,
Thanks for the reply. I resolved the issue using a dedicated ubuntu machine(16.04) rather than using a virtual machine.