Skip to content
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

qnn.conv2d for gigo hw #2

Draft
wants to merge 1 commit into
base: feature/customize-target
Choose a base branch
from
Draft

qnn.conv2d for gigo hw #2

wants to merge 1 commit into from

Conversation

DemonGiggle
Copy link
Owner

To support tflite quantized model for GIGO hw

WIP: try to impl qnn.conv2d for gigo hw
330173c 
The problem is the data type of the quantized model is `unit8` and the
kernel functions (i.e. gigo_conv2d) is `float` type.

Need to have a way to make c-codegen to support `uint8`. This commit
cannot be built.
@DemonGiggle
Copy link
Owner Author

To use TVM parsing the tflite model, the data type should be uint8.

i.e.

mod, params = relay.frontend.from_tflite(tflite_model,
    shape_dict={'input': (1, 224, 224, 3)},
    dtype_dict={'input': 'uint8'})

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
1 participant
@DemonGiggle