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.

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

Fix QAT model converting #2190

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Fix QAT model converting #2190

wants to merge 2 commits into from

Conversation

veralauee
Copy link

Convert quantization aware trained model from TF to ONNX has several issues --

  1. QuantizeLinear and DequantizeLinear are fused into conv layer, but the downstream compiler(e.g., TensorRT) needs the Q/DQ layers to determine whether to use int8 or not. See issue QDQ node for weight tensor of Con2D undergoes Constant folding (enabled for node using tf type=FakeQuantWithMinMaxVarsPerChannel) #1972 . We need to keep Q/DQ layer unfused. QuantizeLinear and DequantizeLinear are corresponding to FakeQuantWithMinMaxVars in TensorFlow, so excluding it from can_fold in tf_utils.py can solve it.
  2. Need to allow narrow_range in quantized nodes. TensorRT maps [min, max] to [-127, 127](see Page 12) , which needs 0 in fp32 to be mapped to 0 in int8. Also see narrow_range=True in TensorRT/tools/tensorflow-quantization here.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants