Self-Created Tools to convert ONNX files (NCHW) to TensorFlow/TFLite/Keras format (NHWC). The purpose of this tool is to solve the massive Transpose extrapolation problem in onnx-tensorflow (onnx-tf). I don't need a Star, but give me a pull request.
An Open Source Machine Learning Framework for Everyone
Convert TensorFlow, Keras, Tensorflow.js and Tflite models to ONNX
pull request commenttensorflow/tensorflow
TFLITE fix inconsistencies in using std/absl for variant/any_cast functions.
Yes, perfectly ok.
comment created time in 24 days
pull request commenttensorflow/tensorflow
TFLITE fix inconsistencies in using std/absl for variant/any_cast functions.
Will try to prepare minimal example, but it may take time.
If you are unsure what this PR fixes, its like if you wrote code like
int * a = new int;
...
free(a); // free instead of delete
which would "work" if the compiler used
void free(void *ptr)
{
delete(ptr);
}
which is often the case, but there is zero guarantee it works always, because the behavior is undefined.
comment created time in a month
pull request commenttensorflow/tensorflow
TFLITE fix inconsistencies in using std/absl for variant/any_cast functions.
Seems not relevant to the commit.
comment created time in 2 months
PR opened PINTO0309/onnx2tf
Parameters were not converted to tf.norm, instead of parameter value, 1 was set because of bool->int conversion.
1. Content and background
LpNormalization conversion does not set parameters axis and p properly.
2. Summary of corrections
removed bool conversion
3. Before/After (If there is an operating log that can be used as a reference)
4. Issue number (only if there is a related issue)
pr created time in 2 months
push eventradekzc/onnx2tf
commit sha 46098417238e70905fd2b5c309a0f12d14deb8e1
LpNormalization.py bugfix - parameters Parameters were not converted to tf.norm, instead of parameter value, 1 was set because of bool->int conversion.
push time in 2 months
fork radekzc/onnx2tf
Self-Created Tools to convert ONNX files (NCHW) to TensorFlow/TFLite/Keras format (NHWC). The purpose of this tool is to solve the massive Transpose extrapolation problem in onnx-tensorflow (onnx-tf). I don't need a Star, but give me a pull request.
fork in 2 months
Convert TensorFlow, Keras, Tensorflow.js and Tflite models to ONNX
fork in 2 months