Hi @Andrey Ignatov
The conversion gives this kind of error with TF1.15, even I set the experimental_new_converter=True.
"ValueError: None is only supported in the 1st dimension. Tensor 'Placeholder' has invalid shape '[1, None, None, 4]'."
It could be work with TF2.3, but the tflite with [1,1,14] input shape
![1616038244022.png 1616038244022.png](https://ai-benchmark.net/data/attachments/0/29-e07bc66bc5312b63799e0111c65820f8.jpg)
And when i try to run it, i got the error message:
""RuntimeError: tensorflow/lite/kernels/kernel_util.cc:404 d1 == d2 || d1 == 1 || d2 == 1 was not true.Node number 11 (MUL) failed to prepare."""
Did you have any advice for me?
By the way, the "Evaluation" section on CodaLab
![1616060887111.png 1616060887111.png](https://ai-benchmark.net/data/attachments/0/30-e1c7789f952e92068d318f84f006025c.jpg)
Does it mean we don't need to generate the model_none.tflite ??
The conversion gives this kind of error with TF1.15, even I set the experimental_new_converter=True.
"ValueError: None is only supported in the 1st dimension. Tensor 'Placeholder' has invalid shape '[1, None, None, 4]'."
It could be work with TF2.3, but the tflite with [1,1,14] input shape
![1616038244022.png 1616038244022.png](https://ai-benchmark.net/data/attachments/0/29-e07bc66bc5312b63799e0111c65820f8.jpg)
And when i try to run it, i got the error message:
""RuntimeError: tensorflow/lite/kernels/kernel_util.cc:404 d1 == d2 || d1 == 1 || d2 == 1 was not true.Node number 11 (MUL) failed to prepare."""
Did you have any advice for me?
By the way, the "Evaluation" section on CodaLab
![1616060887111.png 1616060887111.png](https://ai-benchmark.net/data/attachments/0/30-e1c7789f952e92068d318f84f006025c.jpg)
Does it mean we don't need to generate the model_none.tflite ??
Last edited: