vvchernov commented on code in PR #15723:
URL: https://github.com/apache/tvm/pull/15723#discussion_r1321024911
##########
python/tvm/relay/frontend/keras.py:
##########
@@ -1053,22 +1053,30 @@ def _convert_simple_rnn(
in_data = inexpr[0]
prev_op = inexpr[1]
weightList = keras_layer.get_weights()
- kernel_weight = etab.new_const(weightList[0].transpose([1, 0]))
+ weightList0 = weightList[0].transpose([1, 0])
+ assert len(in_data.type_annotation.shape) == 3
+ for i in range(in_data.type_annotation.shape[1].value - 1):
+ weightList0 = np.hstack((weightList0, weightList[0].transpose([1, 0])))
Review Comment:
Could you check your code for bfloat16 weights? numpy.hstack has dtype arg
and I guess it possibly checks it if so numpy fails when dtype is bfloat16
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
