running_info.log

2023-01-31 06:34:47,478 CHECKBOX VQA STARTED
2023-01-31 06:34:47,478 CHECKBOX ATTRIBUTION DETECTION STARTED
2023-01-31 06:34:53,673 CHECKBOX ATTRIBUTION DETECTION END
2023-01-31 06:34:53,674 CHECKBOX RESULTS STARTED
2023-01-31 06:35:05,345 5 out of the last 5 calls to <function Model.make_predict_function.<locals>.predict_function at 0x7f8f2e4beb80> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for  more details.
2023-01-31 06:35:07,959 6 out of the last 6 calls to <function Model.make_predict_function.<locals>.predict_function at 0x7f8f2e4be9d0> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for  more details.
2023-01-31 06:35:12,565 CHECKBOX RESULTS END
2023-01-31 06:35:12,565 CHECKBOX VQA END
07] WARNING [polymorphic_function.py.called_with_tracing:154] 6 out of the last 6 calls to <function Model.make_predict_function.<locals>.predict_function at 0x7f8f2e4be9d0> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for  more details.
[Tue, 31 Jan 2023 06:35:12] INFO [main.py.<module>:71] CHECKBOX RESULTS END
[Tue, 31 Jan 2023 06:35:12] INFO [main.py.<module>:78] CHECKBOX VQA END