giuseros commented on a change in pull request #7093:
URL: https://github.com/apache/tvm/pull/7093#discussion_r542390418
##########
File path: python/tvm/relay/frontend/tflite.py
##########
@@ -1991,20 +1994,29 @@ def convert_conv(self, op, conv_type):
weight_tensor_type_str = self.get_tensor_type_str(weight_tensor_type)
in_expr = self.get_expr(input_tensor_idx)
- weight_value = self.get_tensor_value(weight_tensor)
-
- # TFLite kernel layout:
- # convolution:
- # OC KH KW IC, we require KH KW IC OC (HWIO)
- # depthwise convolution:
- # 1 KH KW C(input_c * depth_multiplier), we require
- # KH KW IC M (depth_multiplier) (HWOI)
- if is_depthwise_conv:
- weight_value = weight_value.reshape(kernel_h, kernel_w, input_c,
depth_multiplier)
+
+ if self.has_expr(weight_tensor.tensor_idx):
+ weight_expr = self.get_expr(weight_tensor.tensor_idx)
+ if is_depthwise_conv:
+ weight_expr = _op.reshape(
+ weight_expr, (kernel_h, kernel_w, input_c,
depth_multiplier)
+ )
+ else:
+ weight_expr = _op.transpose(weight_expr, axes=(1, 2, 3, 0))
Review comment:
Oh, ok now I see, thanks for the explanation! When you refer to a
Quantize op, you mean a float32->float16 quantization, right? Also, could you
write this in a comment? In this way everyone that will read this can
understand the logic
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
