'2021/02/12'에 해당되는 글 3건

  1. 2021.02.12 피아노 사고싶다 ㅠㅠ
  2. 2021.02.12 ssd_mobilenet_v2 on tf1, tf2
  3. 2021.02.12 소득공제..

중고로 올라왔는데 신품은 낮은 가격은 아니었음에도 평 자체는 좋진 않네

너무 전문적으로 진짜 피이노를 다루던 사람이라 그런가? ㅠㅠ

 

[링크 : http://www.casio-intl.com/kr/ko/emi/products/cdps100/]

'개소리 왈왈 > 육아관련 주저리' 카테고리의 다른 글

재활용 데이  (0) 2021.02.15
시간가는지 모르겠다.  (0) 2021.02.14
피아노 사고싶다 ㅠㅠ  (0) 2021.02.12
고통의 시간.. ㅠㅠ  (2) 2021.01.30
문을 파괴한다!  (0) 2021.01.30
간만에 키즈카페 다녀옴  (0) 2021.01.23
Posted by 구차니

댓글을 달아 주세요

+ 2021.02.16

오는길에 다시 보니 tensorflow model garden / research / object detection 에서 구현된

내용들이지 엄밀하게는 tensorflow 자체의 구현은 아니다.

tensorflow를 가지고 구현한 내용이라고 해야하려나?

-

 

model ssd

type ssd_mobilenet_v2_keras 를

ssd_mobilenet_v2 로 바꾸었더니 아래와 같은 에러가 발생했다.

 

INFO:tensorflow:Maybe overwriting train_steps: 1
I0212 20:50:37.009305 140651210348352 config_util.py:552] Maybe overwriting train_steps: 1
INFO:tensorflow:Maybe overwriting use_bfloat16: False
I0212 20:50:37.009468 140651210348352 config_util.py:552] Maybe overwriting use_bfloat16: False
Traceback (most recent call last):
  File "model_main_tf2.py", line 113, in <module>
    tf.compat.v1.app.run()
  File "/home/minimonk/.local/lib/python3.8/site-packages/tensorflow/python/platform/app.py", line 40, in run
    _run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
  File "/home/minimonk/.local/lib/python3.8/site-packages/absl/app.py", line 303, in run
    _run_main(main, args)
  File "/home/minimonk/.local/lib/python3.8/site-packages/absl/app.py", line 251, in _run_main
    sys.exit(main(argv))
  File "model_main_tf2.py", line 104, in main
    model_lib_v2.train_loop(
  File "/home/minimonk/src/SSD-MobileNet-TF/object_detection/model_lib_v2.py", line 507, in train_loop
    detection_model = MODEL_BUILD_UTIL_MAP['detection_model_fn_base'](
  File "/home/minimonk/src/SSD-MobileNet-TF/object_detection/builders/model_builder.py", line 1106, in build
    return build_func(getattr(model_config, meta_architecture), is_training,
  File "/home/minimonk/src/SSD-MobileNet-TF/object_detection/builders/model_builder.py", line 377, in _build_ssd_model
    _check_feature_extractor_exists(ssd_config.feature_extractor.type)
  File "/home/minimonk/src/SSD-MobileNet-TF/object_detection/builders/model_builder.py", line 249, in _check_feature_extractor_exists
    raise ValueError('{} is not supported. See `model_builder.py` for features '
ValueError: ssd_mobilenet_v2 is not supported. See `model_builder.py` for features extractors compatible with different versions of Tensorflow

 

model_builder.py를 열어보라는데 여러개 파일이 나타난다.?

$ sudo find / -name model_builder.py
/home/minimonk/src/SSD-MobileNet-TF/object_detection/builders/model_builder.py
/home/minimonk/src/SSD-MobileNet-TF/models/research/object_detection/builders/model_builder.py
/home/minimonk/src/SSD-MobileNet-TF/models/research/lstm_object_detection/model_builder.py
/home/minimonk/src/SSD-MobileNet-TF/build/lib/object_detection/builders/model_builder.py

 

lstm 어쩌구를 제외하면 용량이 동일하니 같은 파일로 간주하고 하나를 열어보니 다음과 같이 나오는데..

if tf_version.is_tf2() 에 의해서 사용가능한 녀석은.. 

ssd_mobilenet_v2_fpn_keras 와

ssd_mobilenet_v2_keras 뿐이다 -_-

기대했던 ssd_mobilenet_v2는  tf1 ㅠㅠ

$ vi /home/minimonk/src/SSD-MobileNet-TF/object_detection/builders/model_builder.py
if tf_version.is_tf2():
  from object_detection.models import center_net_hourglass_feature_extractor
  from object_detection.models import center_net_mobilenet_v2_feature_extractor
  from object_detection.models import center_net_mobilenet_v2_fpn_feature_extractor
  from object_detection.models import center_net_resnet_feature_extractor
  from object_detection.models import center_net_resnet_v1_fpn_feature_extractor
  from object_detection.models import faster_rcnn_inception_resnet_v2_keras_feature_extractor as frcnn_inc_res_keras
  from object_detection.models import faster_rcnn_resnet_keras_feature_extractor as frcnn_resnet_keras
  from object_detection.models import ssd_resnet_v1_fpn_keras_feature_extractor as ssd_resnet_v1_fpn_keras
  from object_detection.models import faster_rcnn_resnet_v1_fpn_keras_feature_extractor as frcnn_resnet_fpn_keras
  from object_detection.models.ssd_mobilenet_v1_fpn_keras_feature_extractor import SSDMobileNetV1FpnKerasFeatureExtractor
  from object_detection.models.ssd_mobilenet_v1_keras_feature_extractor import SSDMobileNetV1KerasFeatureExtractor
  from object_detection.models.ssd_mobilenet_v2_fpn_keras_feature_extractor import SSDMobileNetV2FpnKerasFeatureExtractor
  from object_detection.models.ssd_mobilenet_v2_keras_feature_extractor import SSDMobileNetV2KerasFeatureExtractor
  from object_detection.predictors import rfcn_keras_box_predictor
  if sys.version_info[0] >= 3:
    from object_detection.models import ssd_efficientnet_bifpn_feature_extractor as ssd_efficientnet_bifpn

if tf_version.is_tf1():
  from object_detection.models import faster_rcnn_inception_resnet_v2_feature_extractor as frcnn_inc_res
  from object_detection.models import faster_rcnn_inception_v2_feature_extractor as frcnn_inc_v2
  from object_detection.models import faster_rcnn_nas_feature_extractor as frcnn_nas
  from object_detection.models import faster_rcnn_pnas_feature_extractor as frcnn_pnas
  from object_detection.models import faster_rcnn_resnet_v1_feature_extractor as frcnn_resnet_v1
  from object_detection.models import ssd_resnet_v1_fpn_feature_extractor as ssd_resnet_v1_fpn
  from object_detection.models import ssd_resnet_v1_ppn_feature_extractor as ssd_resnet_v1_ppn
  from object_detection.models.embedded_ssd_mobilenet_v1_feature_extractor import EmbeddedSSDMobileNetV1FeatureExtractor
  from object_detection.models.ssd_inception_v2_feature_extractor import SSDInceptionV2FeatureExtractor
  from object_detection.models.ssd_mobilenet_v2_fpn_feature_extractor import SSDMobileNetV2FpnFeatureExtractor
  from object_detection.models.ssd_mobilenet_v2_mnasfpn_feature_extractor import SSDMobileNetV2MnasFPNFeatureExtractor
  from object_detection.models.ssd_inception_v3_feature_extractor import SSDInceptionV3FeatureExtractor
  from object_detection.models.ssd_mobilenet_edgetpu_feature_extractor import SSDMobileNetEdgeTPUFeatureExtractor
  from object_detection.models.ssd_mobilenet_v1_feature_extractor import SSDMobileNetV1FeatureExtractor
  from object_detection.models.ssd_mobilenet_v1_fpn_feature_extractor import SSDMobileNetV1FpnFeatureExtractor
  from object_detection.models.ssd_mobilenet_v1_ppn_feature_extractor import SSDMobileNetV1PpnFeatureExtractor
  from object_detection.models.ssd_mobilenet_v2_feature_extractor import SSDMobileNetV2FeatureExtractor
  from object_detection.models.ssd_mobilenet_v3_feature_extractor import SSDMobileNetV3LargeFeatureExtractor
  from object_detection.models.ssd_mobilenet_v3_feature_extractor import SSDMobileNetV3SmallFeatureExtractor
  from object_detection.models.ssd_mobiledet_feature_extractor import SSDMobileDetCPUFeatureExtractor
  from object_detection.models.ssd_mobiledet_feature_extractor import SSDMobileDetDSPFeatureExtractor
  from object_detection.models.ssd_mobiledet_feature_extractor import SSDMobileDetEdgeTPUFeatureExtractor
  from object_detection.models.ssd_mobiledet_feature_extractor import SSDMobileDetGPUFeatureExtractor
  from object_detection.models.ssd_pnasnet_feature_extractor import SSDPNASNetFeatureExtractor
  from object_detection.predictors import rfcn_box_predictor

 

[링크 : https://stackoverflow.com/questions/65938445/]

 

+

와.. ssd_mobilenet_v2_fpn_keras를 돌리는데 메모리 부족으로 죽어버리네 ㄷㄷ

눈에 보이는건.. additional_layer_depth 인가.. 이걸 줄이고 해봐야 겠네..

    feature_extractor {
      type: 'ssd_mobilenet_v2_fpn_keras'
      use_depthwise: true
      fpn {
        min_level: 3
        max_level: 7
        additional_layer_depth: 128
      }
      min_depth: 16
      depth_multiplier: 1.0
      conv_hyperparams {
        activation: RELU_6,
        regularizer {
          l2_regularizer {
            weight: 0.00004
          }
        }
        initializer {
          random_normal_initializer {
            stddev: 0.01
            mean: 0.0
          }
        }
        batch_norm {
          scale: true,
          decay: 0.997,
          epsilon: 0.001,
        }
      }
      override_base_feature_extractor_hyperparams: true
    }

 

/home/minimonk/.local/lib/python3.8/site-packages/tensorflow/python/keras/backend.py:434: UserWarning: `tf.keras.backend.set_learning_phase` is deprecated and will be removed after 2020-10-11. To update it, simply pass a True/False value to the `training` argument of the `__call__` method of your layer or model.
  warnings.warn('`tf.keras.backend.set_learning_phase` is deprecated and '
2021-02-12 21:23:47.163320: W tensorflow/core/framework/cpu_allocator_impl.cc:80] Allocation of 1258291200 exceeds 10% of free system memory.
죽었음

 

+

depth를 줄이고 해보니 되는척 하다가 또 에러가 발생 ㅋㅋ

    ValueError: Number of feature maps is expected to equal the length of `num_anchors_per_location`.

 

되는 척 하더니 안되네? ㅠㅠ

AssertionError: Some Python objects were not bound to checkpointed values, likely due to changes in the Python program: [MirroredVariable:{
  0: <tf.Variable 'block_8_depthwise/depthwise_kernel:0' shape=(3, 3, 384, 1) dtype=float32, numpy=

...

WARNING:tensorflow:A checkpoint was restored (e.g. tf.train.Checkpoint.restore or tf.keras.Model.load_weights) but not all checkpointed values were used. See above for specific issues. Use expect_partial() on the load status object, e.g. tf.train.Checkpoint.restore(...).expect_partial(), to silence these warnings, or use assert_consumed() to make the check explicit. See https://www.tensorflow.org/guide/checkpoint#loading_mechanics for details.
W0212 21:37:27.939997 140162079770432 util.py:168] A checkpoint was restored (e.g. tf.train.Checkpoint.restore or tf.keras.Model.load_weights) but not all checkpointed values were used. See above for specific issues. Use expect_partial() on the load status object, e.g. tf.train.Checkpoint.restore(...).expect_partial(), to silence these warnings, or use assert_consumed() to make the check explicit. See https://www.tensorflow.org/guide/checkpoint#loading_mechanics for details.

'프로그램 사용 > yolo_tensorflow_golo' 카테고리의 다른 글

tensorflow model 학습 시작지점  (0) 2021.02.18
tensorflow tag set 'serve'  (0) 2021.02.18
ssd_mobilenet_v2 on tf1, tf2  (0) 2021.02.12
fpn - Feature Pyramid Network  (0) 2021.02.11
tensorflow pipeline.config  (0) 2021.02.10
tensorflow pipeline.conf  (0) 2021.02.08
Posted by 구차니

댓글을 달아 주세요

급여가 적어져서 그런가 왜 작년의 절반 수준일까 ㅠㅠ

 

아무튼, 리눅스에서도 되긴 한데

특정 경로가 영 마음에 안드는 곳만 있다는게 문제구만

 

/ 를 잡아두다니.. 어째 불안하다..

'개소리 왈왈 > 직딩의 비애' 카테고리의 다른 글

계단 오르기  (0) 2021.02.21
정신없어!!  (2) 2021.02.16
소득공제..  (0) 2021.02.12
사과가 잘 안팔린다 ㅠㅠ  (0) 2021.02.06
내일부터는 휴가  (0) 2020.12.29
드디어 퇴직금 정산 끝  (0) 2020.12.21
Posted by 구차니

댓글을 달아 주세요