Jupyter kernel keeps dying about vgg16-in-keras HOT 2 CLOSED

Hello,
The issue maybe with the memory availability. Try to change the batch size and step size. Play with the batch size and step size till you find right values for your machines configuration.

from vgg16-in-keras.

UPD: Hi

I changed my instance to t2.xlarge and it seems to be working fine now :)

Hello

I tried to change this, but kernel still eventually dies.

Can you please specify which versions of python and tensorflow to use? For the very first time I believe I used the latest, but then I learned that from tensorflow 2.2.0 fit_generator was deprecated. For this reasons I changes tensorflow to 1.15 and python to 3.7

Now I get new message as follows

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.
2020-07-02 12:36:44.855418: I tensorflow/core/platform/profile_utils/cpu_utils.cc:94] CPU Frequency: 2400070000 Hz
2020-07-02 12:36:44.855638: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x55abac90d1e0 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2020-07-02 12:36:44.855660: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version
OMP: Info #154: KMP_AFFINITY: Initial OS proc set respected: 0
OMP: Info #214: KMP_AFFINITY: decoding x2APIC ids.
OMP: Info #156: KMP_AFFINITY: 1 available OS procs
OMP: Info #157: KMP_AFFINITY: Uniform topology
OMP: Info #285: KMP_AFFINITY: topology layer "LL cache" is equivalent to "socket".
OMP: Info #285: KMP_AFFINITY: topology layer "L3 cache" is equivalent to "socket".
OMP: Info #285: KMP_AFFINITY: topology layer "L2 cache" is equivalent to "socket".
OMP: Info #285: KMP_AFFINITY: topology layer "L1 cache" is equivalent to "socket".
OMP: Info #285: KMP_AFFINITY: topology layer "core" is equivalent to "socket".
OMP: Info #285: KMP_AFFINITY: topology layer "thread" is equivalent to "socket".
OMP: Info #191: KMP_AFFINITY: 1 socket x 1 core/socket x 1 thread/core (1 total cores)
OMP: Info #216: KMP_AFFINITY: OS proc to physical thread map:
OMP: Info #171: KMP_AFFINITY: OS proc 0 maps to socket 0
OMP: Info #252: KMP_AFFINITY: pid 27132 tid 27132 thread 0 bound to OS proc set 0
2020-07-02 12:36:44.857412: I tensorflow/core/common_runtime/process_util.cc:115] Creating new thread pool with default inter op setting: 2. Tune using inter_op_parallelism_threads for best performance.

from vgg16-in-keras.