GPU Environment Tensorflow#

This tutorial is available as an IPython notebook at malaya-speech/example/gpu-environment-tensorflow.

[1]:

import os

os.environ['TF_FORCE_GPU_ALLOW_GROWTH'] = 'true'
os.environ['CUDA_VISIBLE_DEVICES'] = '1'

[6]:

%%time

import malaya_speech
import logging
logging.basicConfig(level = logging.INFO)

WARNING:malaya_speech.streaming:`pyaudio` is not available, `malaya_speech.streaming.stream` is not able to use.

CPU times: user 184 ms, sys: 17.5 ms, total: 201 ms
Wall time: 93.9 ms

List available GPU#

You must install Tensorflow GPU version first to enable GPU hardware acceleration.

[3]:

from tensorflow.python.client import device_lib

device_lib.list_local_devices()

2023-02-09 15:53:12.310410: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2023-02-09 15:53:12.325848: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2023-02-09 15:53:12.328364: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2023-02-09 15:53:12.329202: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2023-02-09 15:53:12.684062: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2023-02-09 15:53:12.684890: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2023-02-09 15:53:12.685553: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2023-02-09 15:53:12.685983: W tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:39] Overriding allow_growth setting because the TF_FORCE_GPU_ALLOW_GROWTH environment variable is set. Original config value was 0.
2023-02-09 15:53:12.685999: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1510] Created device /device:GPU:0 with 22302 MB memory:  -> device: 0, name: NVIDIA GeForce RTX 3090 Ti, pci bus id: 0000:07:00.0, compute capability: 8.6

[3]:

[name: "/device:CPU:0"
 device_type: "CPU"
 memory_limit: 268435456
 locality {
 }
 incarnation: 11493416253575721766,
 name: "/device:GPU:0"
 device_type: "GPU"
 memory_limit: 23385997312
 locality {
   bus_id: 1
   links {
   }
 }
 incarnation: 16395544932201862459
 physical_device_desc: "device: 0, name: NVIDIA GeForce RTX 3090 Ti, pci bus id: 0000:07:00.0, compute capability: 8.6"]

Run model inside GPU#

We can follow steps from here https://www.tensorflow.org/guide/gpu

[4]:

import tensorflow as tf

tf.debugging.set_log_device_placement(True)

[7]:

malaya_speech.stt.ctc.available_transformer()

INFO:malaya_speech.stt:for `malay-fleur102` language, tested on FLEURS102 `ms_my` test set, https://github.com/huseinzol05/malaya-speech/tree/master/pretrained-model/prepare-stt
INFO:malaya_speech.stt:for `malay-malaya` language, tested on malaya-speech test set, https://github.com/huseinzol05/malaya-speech/tree/master/pretrained-model/prepare-stt
INFO:malaya_speech.stt:for `singlish` language, tested on IMDA malaya-speech test set, https://github.com/huseinzol05/malaya-speech/tree/master/pretrained-model/prepare-stt

[7]:
Size (MB) Quantized Size (MB) malay-malaya Language
hubert-conformer-tiny 36.6 10.3 {'WER': 0.238714008166, 'CER': 0.060899814, 'W... [malay]
hubert-conformer 115 31.1 {'WER': 0.2387140081, 'CER': 0.06089981404, 'W... [malay]
hubert-conformer-large 392 100 {'WER': 0.2203140421, 'CER': 0.0549270416, 'WE... [malay]

Malaya frozen graph interfaces#

load graph#

All the malaya tensorflow model interface will pass vector arguments to malaya_boilerplate.frozen_graph.load_graph,

def load_graph(package, frozen_graph_filename, **kwargs):
    """
    Load frozen graph from a checkpoint.

    Parameters
    ----------
    frozen_graph_filename: str
    precision_mode: str, optional (default='FP32')
        change precision frozen graph, only supported one of ['BFLOAT16', 'FP16', 'FP32', 'FP64'].
    device: str, optional (default='CPU:0')
        device to use for specific model, read more at https://www.tensorflow.org/guide/gpu

    Returns
    -------
    result : tensorflow.Graph
    """

generate session#

After get load into the graph, it will pass the graph into malaya_boilerplate.frozen_graph.generate_session to generate session for Tensorflow graph,

def generate_session(graph, **kwargs):
    """
    Load session for a Tensorflow graph.

    Parameters
    ----------
    graph: tensorflow.Graph
    gpu_limit: float, optional (default = 0.999)
        limit percentage to use a gpu memory.

    Returns
    -------
    result : tensorflow.Session
    """

[8]:

tiny = malaya_speech.stt.ctc.transformer(model = 'hubert-conformer-tiny', device = 'GPU:0')

2023-02-09 15:54:01.508535: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2023-02-09 15:54:01.509432: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2023-02-09 15:54:01.510104: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2023-02-09 15:54:01.530884: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2023-02-09 15:54:01.531653: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2023-02-09 15:54:01.532178: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1510] Created device /device:GPU:0 with 22302 MB memory:  -> device: 0, name: NVIDIA GeForce RTX 3090 Ti, pci bus id: 0000:07:00.0, compute capability: 8.6
2023-02-09 15:54:03.235117: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2023-02-09 15:54:03.235827: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2023-02-09 15:54:03.236258: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2023-02-09 15:54:03.236728: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2023-02-09 15:54:03.237151: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2023-02-09 15:54:03.237569: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1510] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 22302 MB memory:  -> device: 0, name: NVIDIA GeForce RTX 3090 Ti, pci bus id: 0000:07:00.0, compute capability: 8.6

[9]:

y, _ = malaya_speech.load('speech/example-speaker/husein-zolkepli.wav')

[11]:

tiny.predict([y])

2023-02-09 15:55:01.695095: I tensorflow/stream_executor/cuda/cuda_dnn.cc:369] Loaded cuDNN version 8302
2023-02-09 15:55:02.590549: I tensorflow/core/platform/default/subprocess.cc:304] Start cannot spawn child process: No such file or directory
2023-02-09 15:55:02.680280: I tensorflow/stream_executor/cuda/cuda_blas.cc:1760] TensorFloat-32 will be used for the matrix multiplication. This will only be logged once.

Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op CTCBeamSearchDecoder in device /job:localhost/replica:0/task:0/device:CPU:0
WARNING:tensorflow:From /home/husein/dev/malaya-speech/malaya_speech/model/wav2vec.py:66: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use `tf.cast` instead.

2023-02-09 15:55:02.788906: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2023-02-09 15:55:02.789677: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2023-02-09 15:55:02.790159: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2023-02-09 15:55:02.790921: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2023-02-09 15:55:02.791811: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2023-02-09 15:55:02.792488: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2023-02-09 15:55:02.792915: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2023-02-09 15:55:02.793309: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2023-02-09 15:55:02.793700: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1510] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 22302 MB memory:  -> device: 0, name: NVIDIA GeForce RTX 3090 Ti, pci bus id: 0000:07:00.0, compute capability: 8.6
WARNING:tensorflow:From /home/husein/dev/malaya-speech/malaya_speech/model/wav2vec.py:66: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use `tf.cast` instead.

Executing op Cast in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op Fill in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op SparseToDense in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op StridedSlice in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op StridedSlice in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op StridedSlice in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op StridedSlice in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op StridedSlice in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op StridedSlice in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op StridedSlice in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op StridedSlice in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op StridedSlice in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op StridedSlice in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op StridedSlice in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op StridedSlice in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op StridedSlice in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op StridedSlice in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op StridedSlice in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op StridedSlice in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op StridedSlice in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op StridedSlice in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op StridedSlice in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op StridedSlice in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op StridedSlice in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op StridedSlice in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op StridedSlice in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op StridedSlice in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op StridedSlice in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op StridedSlice in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op StridedSlice in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op StridedSlice in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op StridedSlice in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op StridedSlice in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op StridedSlice in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op StridedSlice in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op StridedSlice in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op StridedSlice in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op StridedSlice in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op StridedSlice in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op _EagerConst in device /job:localhost/replica:0/task:0/device:GPU:0
Executing op StridedSlice in device /job:localhost/replica:0/task:0/device:GPU:0

[11]:

['testing nama saya busin bian zokeple']

[12]:

!nvidia-smi

Thu Feb  9 15:55:17 2023
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 470.161.03   Driver Version: 470.161.03   CUDA Version: 11.4     |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|                               |                      |               MIG M. |
|===============================+======================+======================|
|   0  NVIDIA GeForce ...  Off  | 00000000:01:00.0 Off |                  Off |
| 47%   61C    P2   345W / 350W |  22423MiB / 24256MiB |     97%      Default |
|                               |                      |                  N/A |
+-------------------------------+----------------------+----------------------+
|   1  NVIDIA GeForce ...  Off  | 00000000:07:00.0 Off |                  Off |
|  0%   47C    P2   106W / 350W |   4146MiB / 24256MiB |      0%      Default |
|                               |                      |                  N/A |
+-------------------------------+----------------------+----------------------+

+-----------------------------------------------------------------------------+
| Processes:                                                                  |
|  GPU   GI   CI        PID   Type   Process name                  GPU Memory |
|        ID   ID                                                   Usage      |
|=============================================================================|
|    0   N/A  N/A    809903      C   python3                         22421MiB |
|    1   N/A  N/A   1243519      C   /usr/bin/python3                 2481MiB |
|    1   N/A  N/A   1244555      C   /usr/bin/python3                 1663MiB |
+-----------------------------------------------------------------------------+