[GitHub] [tvm] giuseros commented on a change in pull request #7093: [TFLite] add support for float16

[GitBox <gi...@apache.org>]

giuseros commented on a change in pull request #7093:
URL: https://github.com/apache/tvm/pull/7093#discussion_r542233725



##########
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:
       Few questions about this: 
   * is this related to `float16` support? 
   * is your test hitting this code?
   * could you write some comment to explain when this branch is taken and why?
   
   Same questions hold for the bias later




----------------------------------------------------------------
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:
users@infra.apache.org