models icon indicating copy to clipboard operation
models copied to clipboard

occur "UnicodeDecodeError"

Open emi-wada opened this issue 2 years ago • 3 comments

I tried to move quantize_movinet.py. However, when I try to quantize movinet for int8, such as python quantize_movinet.py --saved_model_dir=${SAVED_MODEL_DIR} --saved_model_with_states_dir=${SAVED_MODEL_WITH_STATES_DIR} --output_dataset_dir=${OUTPUT_DATASET_DIR} --output_tflite=${OUTPUT_TFLITE} --quantization_mode=int8 --save_dataset_to_tfrecords=True

I get following error UnicodeDecodeError: 'utf-8' codec can't decode byte 0x8e in position 193: invalid start byte

What does it mean? I guess Kinetics600 dataset doesn't work well. So, I added here in line 86 input_path='C:\\Users\\~~\\kinetics600\\', However it doesn't work. Please tell me how to move "quantize_movinet.py." Thanks.

OS: Windows Python 3.9

emi-wada avatar Jan 03 '23 05:01 emi-wada

Hi @fyangf,

Could you please look at this once in your free time.

Thanks.

laxmareddyp avatar Jan 09 '23 18:01 laxmareddyp

Pinged @yuanliangzhe offline

fyangf avatar Jan 31 '23 18:01 fyangf

Could you paste the whole trace for debugging so the author can take a look?

fyangf avatar Feb 01 '23 16:02 fyangf

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you.

google-ml-butler[bot] avatar Mar 01 '23 23:03 google-ml-butler[bot]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you.

google-ml-butler[bot] avatar Mar 08 '23 23:03 google-ml-butler[bot]

Closing as stale. Please reopen if you'd like to work on this further. Thanks

laxmareddyp avatar Mar 13 '23 17:03 laxmareddyp

Are you satisfied with the resolution of your issue? Yes No

google-ml-butler[bot] avatar Mar 13 '23 17:03 google-ml-butler[bot]