New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

how to conver to tflite #26

Open

fangxiaoying opened this issue Aug 9, 2021 · 0 comments

fangxiaoying commented Aug 9, 2021

I want to convert Lightnet_0.75 to tflite and quant to deploy it on NPU.

input_shape=(320,320,3)

saved_model_dir='./model/Lightnet_0.75/detector'
saved_model_dir_for_lite=saved_model_dir+'lite_pre'

we build the tflite version detect firstly, then save it

model=DSFDLite(input_shape)
model.load_weights(saved_model_dir+'/variables/variables')
tf.saved_model.save(model,saved_model_dir_for_lite)

print('the model rebuild over, ')

but meet error.ValueError: Tensor's shape (1, 1, 16, 32) is not compatible with supplied shape (1, 1, 24, 24)

How to fix? thank!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment