Search results

I remove these two lines of code and the conversion still outputs the same error。 2.The model convert code as follow: converter = tf.lite.TFLiteConverter.from_keras_model(model_tf.build(input_shape=(1,None,None,30))) tflite_model = converter.convert()

I have submit a ZIP archive to the test phase, but it failed. The error log is : WARNING: Your kernel does not support swap limit capabilities or the cgroup is not mounted. Memory limited without swap. Traceback (most recent call last): File "/tmp/codalab/tmp2t1TT8/run/program/evaluate.py"...

1.we cannot convert our model to 'model_none.tflite' while 'model.tflite' is converted successful. The error messages show in file 'log.txt'. The network is realized by tf.keras ,it seems not support tf.transpose ops with None dims while converting to TFLITE. 2.The model convert code as...

Hi, I have set the experimental_new_converter option to True by default，but still cannot convert tf to model_none.tflite。Are there any other parameters that need to be set？ My tf version is 2.4

Hi，When will the runtime validation server online ?

Hi，Can I submit val dataset results and get the score now? I see there is only one submitted result on codalab. Are there examples of submission formats about ZIP archive?

The input tensor of tflite model should accept 10 subsequent video frames and have a size of [1 x 180 x 320 x 30]. How to calculate the runtime of the model？ Devide the AI-Benchmark output 'Avg latency' by 10 is the runtime per frame?