I ran Python code in Spyder to train some neural networks with different parameters back-to back in Keras overnight (i.e, train Model 1, train Model 2.. ), and came back to find this error:
An error ocurred while starting the kernel 2020 12:32:54.985379: I tensorflow/core/platform/cpu_feature_guard.cc:145] This TensorFlow binary is optimized with Intel(R) MKL‑DNN to use the following CPU instructions in performance critical operations: SSE4.1 SSE4.2 AVX AVX2 FMA To enable them in non‑MKL‑DNN operations, rebuild TensorFlow with the appropriate compiler flags. 2020 12:32:54.985817: I tensorflow/core/common_runtime/process_util.cc:115] Creating new thread pool with default inter op setting: 16. Tune using inter_op_parallelism_threads for best performance.
Does this mean that it dropped because the CPU usage was too high?
And also, Spyder suggests that it is still loading, so is it still training a network? I set verbose to 0 so not sure now if it is completing things/executing the code.