Darkflow: μƒˆ 데이터 μ„ΈνŠΈ ꡐ윑 였λ₯˜ - "AttributeError: 'NoneType' κ°œμ²΄μ— 'shape' 속성이 μ—†μŠ΅λ‹ˆλ‹€."

에 λ§Œλ“  2017λ…„ 05μ›” 30일  Β·  23μ½”λ©˜νŠΈ  Β·  좜처: thtrieu/darkflow

μ•ˆλ…•,

λ‚˜λŠ” μƒˆλ‘œμš΄ 데이터 μ„ΈνŠΈλ₯Ό ν›ˆλ ¨ν•˜κ³  μžˆμŠ΅λ‹ˆλ‹€. κ·ΈλŸ¬λ‚˜ ν›ˆλ ¨μ€ 항상 λͺ‡ 단계 λ™μ•ˆ μ‹€ν–‰λ˜λ©° κ°‘μžκΈ° λ‹€μŒ 였λ₯˜κ°€ λ°œμƒν•©λ‹ˆλ‹€. "AttributeError: 'NoneType' object has no attribute 'shape'". ꡐ윑이 λͺ‡ 단계 λ™μ•ˆ 싀행될 수 있고 μΆ”κ°€ 문제 ν•΄κ²° 방법에 λŒ€ν•œ 아이디어가 μ‹€ν–‰λ˜κ³  μžˆμœΌλ―€λ‘œ 주석 파일의 주석 ν˜•μ‹κ³Ό 파일 이름이 μ •ν™•ν•˜λ‹€κ³  μƒκ°ν•©λ‹ˆλ‹€.

이에 λŒ€ν•œ μ•„μ΄λ””μ–΄λ‚˜ 도움에 κ°μ‚¬λ“œλ¦½λ‹ˆλ‹€.

κ°μ‚¬ν•©λ‹ˆλ‹€.

root<strong i="9">@dd84391fd870</strong>:/ml/darkflow# flow --model cfg/tiny-yolo-new.cfg --train --dataset "../data/new/JPEGImages" --annotation "../data/new/Annotations"

Parsing cfg/tiny-yolo-new.cfg
Loading None ...
Finished in 0.00011324882507324219s

Building net ...
Source | Train? | Layer description                | Output size
-------+--------+----------------------------------+---------------
       |        | input                            | (?, 416, 416, 3)
 Init  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 416, 416, 16)
 Load  |  Yep!  | maxp 2x2p0_2                     | (?, 208, 208, 16)
 Init  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 208, 208, 32)
 Load  |  Yep!  | maxp 2x2p0_2                     | (?, 104, 104, 32)
 Init  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 104, 104, 64)
 Load  |  Yep!  | maxp 2x2p0_2                     | (?, 52, 52, 64)
 Init  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 52, 52, 128)
 Load  |  Yep!  | maxp 2x2p0_2                     | (?, 26, 26, 128)
 Init  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 26, 26, 256)
 Load  |  Yep!  | maxp 2x2p0_2                     | (?, 13, 13, 256)
 Init  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 13, 13, 512)
 Load  |  Yep!  | maxp 2x2p0_1                     | (?, 13, 13, 512)
 Init  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 13, 13, 1024)
 Init  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 13, 13, 1024)
 Init  |  Yep!  | conv 1x1p0_1    linear           | (?, 13, 13, 40)
-------+--------+----------------------------------+---------------
Running entirely on CPU
cfg/tiny-yolo-new.cfg loss hyper-parameters:
    H       = 13
    W       = 13
    box     = 5
    classes = 3
    scales  = [1.0, 5.0, 1.0, 1.0]
Building cfg/tiny-yolo-new.cfg loss
Building cfg/tiny-yolo-new.cfg train op
W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE3 instructions, but these are available on your machine and could speed up CPU computations.
W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
Finished in 7.207982778549194s

Enter training ...

cfg/tiny-yolo-new.cfg parsing ../data/new/Annotations
Parsing for ['tank', 'truck', 'apc'] 
[====================>]100%  000296.xml
Statistics:
apc: 48
tank: 70
truck: 24
Dataset size: 130
Dataset of 130 instance(s)
Training statistics: 
    Learning rate : 1e-05
    Batch size    : 16
    Epoch number  : 1000
    Backup every  : 2000
step 1 - loss 106.16172790527344 - moving ave loss 106.16172790527344
step 2 - loss 106.1773681640625 - moving ave loss 106.16329193115234
step 3 - loss 106.09341430664062 - moving ave loss 106.15630416870117
step 4 - loss 106.24054718017578 - moving ave loss 106.16472846984863
step 5 - loss 106.12216186523438 - moving ave loss 106.1604718093872
step 6 - loss 106.24075317382812 - moving ave loss 106.1684999458313
Traceback (most recent call last):
  File "/usr/local/bin/flow", line 6, in <module>
    cliHandler(sys.argv)
  File "/usr/local/lib/python3.5/dist-packages/darkflow/cli.py", line 29, in cliHandler
    print('Enter training ...'); tfnet.train()
  File "/usr/local/lib/python3.5/dist-packages/darkflow/net/flow.py", line 37, in train
    for i, (x_batch, datum) in enumerate(batches):
  File "/usr/local/lib/python3.5/dist-packages/darkflow/net/yolo/data.py", line 113, in shuffle
    inp, new_feed = self._batch(train_instance)
  File "/usr/local/lib/python3.5/dist-packages/darkflow/net/yolov2/data.py", line 27, in _batch
    img = self.preprocess(path, allobj)
  File "/usr/local/lib/python3.5/dist-packages/darkflow/net/yolo/predict.py", line 61, in preprocess
    result = imcv2_affine_trans(im)
  File "/usr/local/lib/python3.5/dist-packages/darkflow/utils/im_transform.py", line 19, in imcv2_affine_trans
    h, w, c = im.shape
AttributeError: 'NoneType' object has no attribute 'shape'

κ°€μž₯ μœ μš©ν•œ λŒ“κΈ€

λ‚˜λŠ” 과거에 이것을 λ§Œλ‚¬λ‹€. 일뢀 .xml λ˜λŠ” .jpg 파일이 μ œλŒ€λ‘œ λͺ…λͺ…/κ΅¬μ„±λ˜μ§€ μ•Šμ•˜μ„ κ°€λŠ₯성이 λ†’μŠ΅λ‹ˆλ‹€. 무엇이 잘λͺ»λ˜μ—ˆλŠ”지 λ””λ²„κΉ…ν•˜λŠ” ν•œ 가지 방법은 λ‹€μŒμ„ μΆ”κ°€ν•˜λŠ” κ²ƒμž…λ‹ˆλ‹€.

print(jpg)

이 쀄 이후: https://github.com/thtrieu/darkflow/blob/master/darkflow/net/yolov2/data.py#L26

λ”°λΌμ„œ μ†μƒλœ 파일의 이름을 보고 .xml λ˜λŠ” .jpg 쀑 ν•˜λ‚˜λ₯Ό 쑰사할 수 μžˆμŠ΅λ‹ˆλ‹€.

λͺ¨λ“  23 λŒ“κΈ€

xml νŒŒμΌμ„ ν™•μΈν•˜μ‹­μ‹œμ˜€. 파일 이름에 이미지 ν™•μž₯μžκ°€ ν¬ν•¨λ˜μ–΄ μžˆμŠ΅λ‹ˆκΉŒ?

예, 파일 μ΄λ¦„μ—λŠ” λ‚΄ μ΄λ―Έμ§€μ˜ ν™•μž₯μžκ°€ .jpg둜 ν¬ν•¨λ˜μ–΄ μžˆμŠ΅λ‹ˆλ‹€.

λ‹€μŒμ€ xml 파일 쀑 ν•˜λ‚˜μž…λ‹ˆλ‹€.

<annotation>
  <folder>JPEGImages</folder>
  <filename>/ml/data/new/JPEGImages/000004.jpg</filename>
  <source>
    <database>Unknown</database>
  </source>
  <size>
    <width>386</width>
    <height>257</height>
    <depth>3</depth>
  </size>
  <segmented>0</segmented>
  <object>
    <name>tank</name>
    <pose>Unspecified</pose>
    <truncated>0</truncated>
    <difficult>0</difficult>
    <bndbox>
      <xmin>80</xmin>
      <ymin>51</ymin>
      <xmax>357</xmax>
      <ymax>220</ymax>
    </bndbox>
  </object>
</annotation>

@wendq86 그것이 μž‘λ™ν•˜μ§€ μ•ŠλŠ” 것을 보면 - 경둜 없이 파일 이름을 넣어보고(예: <filename>000004.jpg</filename> ) ν›ˆλ ¨μ„ μ‹œλ„ν•  λ•Œ λ³€κ²½λ˜λŠ” 사항이 μžˆλŠ”μ§€ 확인할 수 μžˆμŠ΅λ‹ˆκΉŒ?

@abagshaw μ œμ•ˆ κ°μ‚¬ν•©λ‹ˆλ‹€. 경둜 없이 파일 이름을 λ„£μœΌλ €κ³  ν–ˆμ§€λ§Œ μ—¬μ „νžˆ λ™μΌν•œ 였λ₯˜κ°€ λ°œμƒν•©λ‹ˆλ‹€.

λ‹€λ₯Έ 아이디어가 μžˆμŠ΅λ‹ˆκΉŒ?

root<strong i="8">@154b72514519</strong>:/ml/darkflow# flow --model cfg/tiny-yolo-new.cfg --train --dataset "/ml/data/new/JPEGImages" --annotation "/ml/data/new/Annotations"

Parsing cfg/tiny-yolo-new.cfg
Loading None ...
Finished in 0.00011515617370605469s

Building net ...
Source | Train? | Layer description                | Output size
-------+--------+----------------------------------+---------------
       |        | input                            | (?, 416, 416, 3)
 Init  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 416, 416, 16)
 Load  |  Yep!  | maxp 2x2p0_2                     | (?, 208, 208, 16)
 Init  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 208, 208, 32)
 Load  |  Yep!  | maxp 2x2p0_2                     | (?, 104, 104, 32)
 Init  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 104, 104, 64)
 Load  |  Yep!  | maxp 2x2p0_2                     | (?, 52, 52, 64)
 Init  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 52, 52, 128)
 Load  |  Yep!  | maxp 2x2p0_2                     | (?, 26, 26, 128)
 Init  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 26, 26, 256)
 Load  |  Yep!  | maxp 2x2p0_2                     | (?, 13, 13, 256)
 Init  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 13, 13, 512)
 Load  |  Yep!  | maxp 2x2p0_1                     | (?, 13, 13, 512)
 Init  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 13, 13, 1024)
 Init  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 13, 13, 1024)
 Init  |  Yep!  | conv 1x1p0_1    linear           | (?, 13, 13, 40)
-------+--------+----------------------------------+---------------
Running entirely on CPU
cfg/tiny-yolo-new.cfg loss hyper-parameters:
    H       = 13
    W       = 13
    box     = 5
    classes = 3
    scales  = [1.0, 5.0, 1.0, 1.0]
Building cfg/tiny-yolo-new.cfg loss
Building cfg/tiny-yolo-new.cfg train op
W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE3 instructions, but these are available on your machine and could speed up CPU computations.
W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
Finished in 6.813853979110718s

Enter training ...

cfg/tiny-yolo-new.cfg parsing /ml/data/new/Annotations
Parsing for ['tank', 'truck', 'apc'] 
[====================>]100%  000296.xml
Statistics:
tank: 70
truck: 24
apc: 48
Dataset size: 130
Dataset of 130 instance(s)
Training statistics: 
    Learning rate : 1e-05
    Batch size    : 16
    Epoch number  : 1000
    Backup every  : 2000
step 1 - loss 105.96209716796875 - moving ave loss 105.96209716796875
step 2 - loss 105.95611572265625 - moving ave loss 105.9614990234375
step 3 - loss 105.87786865234375 - moving ave loss 105.95313598632812
Traceback (most recent call last):
  File "/usr/local/bin/flow", line 6, in <module>
    cliHandler(sys.argv)
  File "/usr/local/lib/python3.5/dist-packages/darkflow/cli.py", line 29, in cliHandler
    print('Enter training ...'); tfnet.train()
  File "/usr/local/lib/python3.5/dist-packages/darkflow/net/flow.py", line 37, in train
    for i, (x_batch, datum) in enumerate(batches):
  File "/usr/local/lib/python3.5/dist-packages/darkflow/net/yolo/data.py", line 113, in shuffle
    inp, new_feed = self._batch(train_instance)
  File "/usr/local/lib/python3.5/dist-packages/darkflow/net/yolov2/data.py", line 27, in _batch
    img = self.preprocess(path, allobj)
  File "/usr/local/lib/python3.5/dist-packages/darkflow/net/yolo/predict.py", line 61, in preprocess
    result = imcv2_affine_trans(im)
  File "/usr/local/lib/python3.5/dist-packages/darkflow/utils/im_transform.py", line 19, in imcv2_affine_trans
    h, w, c = im.shape
AttributeError: 'NoneType' object has no attribute 'shape'

@wendq86 μ΄μƒν•œ 점은 첫 번째 λ‹¨κ³„μ—μ„œ 였λ₯˜κ°€ λ°œμƒν•˜μ§€ μ•ŠλŠ”λ‹€λŠ” κ²ƒμž…λ‹ˆλ‹€...μ΄λŠ” .xml 파일 쀑 μΌλΆ€λŠ” μ œλŒ€λ‘œ κ΅¬μ„±λ˜κ³  λ‚˜λ¨Έμ§€λŠ” 그렇지 μ•Šλ‹€λŠ” 것을 λ‚˜νƒ€λ‚Ό 수 μžˆμŠ΅λ‹ˆλ‹€. 파일의 _λͺ¨λ“ _이 <filename>000004.jpg</filename> ν˜•μ‹μ„ μ‚¬μš©ν•œλ‹€κ³  100% ν™•μ‹ ν•˜μ‹­λ‹ˆκΉŒ? ν•˜λ‚˜(λ˜λŠ” κ·Έ 이상)κ°€ μ œλŒ€λ‘œ κ΅¬μ„±λ˜μ§€ μ•Šμ•˜μ„ κ°€λŠ₯성이 μžˆμŠ΅λ‹ˆκΉŒ? 이 λͺ¨λ“  파일의 ν˜•μ‹μ„ μ–΄λ–»κ²Œ μˆ˜μ •ν•˜κ³  μžˆλŠ”μ§€ 잘 λͺ¨λ₯΄κ² μŠ΅λ‹ˆλ‹€... ν•˜μ§€λ§Œ 도ꡬλ₯Ό μ‚¬μš©ν•˜μ—¬ λ§Žμ€ νŒŒμΌμ„ 일괄 μˆ˜μ •ν•˜λŠ” 경우 일뢀가 λˆ„λ½λ  수 μžˆμŠ΅λ‹ˆκΉŒ?

λ‚΄κ°€ 생각할 μˆ˜μžˆλŠ” μœ μΌν•œ λ‹€λ₯Έ 것은 일뢀 이미지가 /ml/data/new/JPEGImages μ—μ„œ μ œκ±°λ˜μ—ˆμ§€λ§Œ ν•΄λ‹Ή .xml 파일이 /ml/data/new/Annotations μ—μ„œ μ œκ±°λ˜μ§€ μ•Šμ•˜λ‹€λŠ” κ²ƒμž…λ‹ˆλ‹€. /ml/data/new/JPEGImages 에 μžˆλŠ” 이미지와 같은 수의 .xml 파일이 /ml/data/new/Annotations $ 에 μžˆμŠ΅λ‹ˆκΉŒ?

λ‚˜λŠ” 과거에 이것을 λ§Œλ‚¬λ‹€. 일뢀 .xml λ˜λŠ” .jpg 파일이 μ œλŒ€λ‘œ λͺ…λͺ…/κ΅¬μ„±λ˜μ§€ μ•Šμ•˜μ„ κ°€λŠ₯성이 λ†’μŠ΅λ‹ˆλ‹€. 무엇이 잘λͺ»λ˜μ—ˆλŠ”지 λ””λ²„κΉ…ν•˜λŠ” ν•œ 가지 방법은 λ‹€μŒμ„ μΆ”κ°€ν•˜λŠ” κ²ƒμž…λ‹ˆλ‹€.

print(jpg)

이 쀄 이후: https://github.com/thtrieu/darkflow/blob/master/darkflow/net/yolov2/data.py#L26

λ”°λΌμ„œ μ†μƒλœ 파일의 이름을 보고 .xml λ˜λŠ” .jpg 쀑 ν•˜λ‚˜λ₯Ό 쑰사할 수 μžˆμŠ΅λ‹ˆλ‹€.

@abagshaw 와 @thtrieuμ—κ²Œ κ°μ‚¬λ“œλ¦½λ‹ˆλ‹€! λ„ˆλΉ„, 높이, ymin, ymax, xmin 및 xmax 값을 ν™•μΈν•˜κΈ° μœ„ν•΄ xml νŒŒμΌμ„ ꡬ문 λΆ„μ„ν•˜λŠ” Python 슀크립트λ₯Ό μž‘μ„±ν•˜μ—¬ 문제의 원인을 μ°Ύμ•˜μŠ΅λ‹ˆλ‹€. λ¬Έμ œλŠ” opencvμ—μ„œ μ œλŒ€λ‘œ λ‘œλ“œν•  수 μ—†λŠ” 두 개의 jpg 파일둜 인해 λ°œμƒν•˜λ―€λ‘œ labelImgμ—μ„œ μž‘μ„±ν•œ xml νŒŒμΌμ—μ„œ λ„ˆλΉ„μ™€ 높이가 0으둜 μ§€μ •λ©λ‹ˆλ‹€.

@thtrieu 의 μ œμ•ˆμ€ λ§Žμ€ 도움이 λ©λ‹ˆλ‹€. 문제 .jpg λ˜λŠ” .xml을 μ°ΎκΈ° μœ„ν•΄ 인쇄λ₯Ό μ‚¬μš©ν•˜μ§€ μ•Šμ•˜μŠ΅λ‹ˆλ‹€.
darkflowλ₯Ό μ‹œμž‘ν•˜λŠ” μ‚¬λžŒμ΄λΌλ©΄ λˆ„κ΅¬λ‚˜ μžμ‹ μ˜ ν™˜κ²½μ—μ„œ μž‘λ™ν•˜λŠ”μ§€ ν™•μΈν•˜κ³  싢을 λΏμž…λ‹ˆλ‹€. λ‚΄κ°€ 생각해 λ‚Έ 문제둜 인해 μ—¬κΈ°μ—μ„œ μž‘μ€ 결둠을 λ‚΄λ ΈμŠ΅λ‹ˆλ‹€.

  1. darkflow-master/test/training/annotations 및 .../images의 데이터λ₯Ό μ‚¬μš©ν•˜λ―€λ‘œ VOCformat 도ꡬλ₯Ό κ³ λ €ν•  ν•„μš”κ°€ μ—†μŠ΅λ‹ˆλ‹€. 여기에 두 개의 .xml 파일이 μžˆμŠ΅λ‹ˆλ‹€. (1.xml, 2.xml)
  2. μžμ‹ μ˜ _test_labels.txt_λ₯Ό λ§Œλ“€κ³  λ°μ΄ν„°λ‘œ 인해 3개의 클래슀 이름을 μž…λ ₯ν•©λ‹ˆλ‹€(말과 μžμ „κ±°λ₯Ό νƒ€λŠ” 두 개의 μ‚¬μ§„λ§Œ .xmlμ—μ„œ 클래슀 이름을 κ°€μ Έμ˜¬ 수 μžˆμŠ΅λ‹ˆλ‹€. μ—΄μ–΄ ν™•μΈν•˜μ‹­μ‹œμ˜€).
    μ‚¬λžŒ
    μžμ „κ±°
    말
  3. .cfg νŒŒμΌμ—μ„œ _classes_ nad _filters_λ₯Ό λ³€κ²½ν•˜κ³  *.cfg의 이름을 λ³€κ²½ν•΄μ•Ό ν•©λ‹ˆλ‹€. 그렇지 μ•ŠμœΌλ©΄ λ‹€λ₯Έ 문제 λ¬Έμ œκ°€ λ°œμƒν•˜κ³  μ‚¬μš©ν•˜λ €λŠ” .weightsλ₯Ό λ³€κ²½ν•˜μ§€ λ§ˆμ‹­μ‹œμ˜€. 그렇지 μ•ŠμœΌλ©΄ λ‹€λ₯Έ 문제 λ¬Έμ œκ°€ λ°œμƒν•©λ‹ˆλ‹€.
  4. λ‹€μŒ μ½”λ“œλ₯Ό μ‹€ν–‰ν•˜μ—¬ ν™˜κ²½μ—μ„œ μ‹€ν–‰λ˜λŠ”μ§€ ν™•μΈν•˜μ‹­μ‹œμ˜€.
    flow --model ../tiny-yolo-voc-try.cfg --load ../tiny-yolo-voc.weights --labels ../test_labels.txt --train --annotation ../annotations --dataset ../images --gpu 1.0

wendq86 슀크립트λ₯Ό κ³΅μœ ν•΄ μ£Όμ‹€ 수 μžˆμŠ΅λ‹ˆκΉŒ?

λ‚˜λŠ” 과거에 이것을 λ§Œλ‚¬λ‹€. 일뢀 .xml λ˜λŠ” .jpg 파일이 μ œλŒ€λ‘œ λͺ…λͺ…/κ΅¬μ„±λ˜μ§€ μ•Šμ•˜μ„ κ°€λŠ₯성이 λ†’μŠ΅λ‹ˆλ‹€. 무엇이 잘λͺ»λ˜μ—ˆλŠ”지 λ””λ²„κΉ…ν•˜λŠ” ν•œ 가지 방법은 λ‹€μŒμ„ μΆ”κ°€ν•˜λŠ” κ²ƒμž…λ‹ˆλ‹€.

print(jpg)

이 쀄 이후: https://github.com/thtrieu/darkflow/blob/master/darkflow/net/yolov2/data.py#L26

λ”°λΌμ„œ μ†μƒλœ 파일의 이름을 보고 .xml λ˜λŠ” .jpg 쀑 ν•˜λ‚˜λ₯Ό 쑰사할 수 μžˆμŠ΅λ‹ˆλ‹€.

jpeg인 경우 문제λ₯Ό ν•΄κ²°ν•˜λ €λ©΄ μ–΄λ–»κ²Œ ν•΄μ•Ό ν•©λ‹ˆκΉŒ? λ‚˜λŠ” 같은 λ¬Έμ œκ°€ μžˆμ—ˆκ³  인쇄 문을 μ‹€ν–‰ν–ˆμŠ΅λ‹ˆλ‹€.

λ‚˜λŠ”μ΄ 좜λ ₯을 μ–»μ—ˆλ‹€ :

cfg/yolov2-tiny-c1v2.cfg parsing lung_train/annotations
Parsing for ['Opacity']
[====================>]100%  012a5620-d082-4bb8-9b3b-e72d8938000c.xml
Statistics:
Opacity: 11
Dataset size: 6
Dataset of 6 instance(s)
**010ccb9f-6d46-4380-af11-84f87397a1b8.jpg
00c0b293-48e7-4e16-ac76-9269ba535a62**

두 번째 이미지 파일 뒀에 .jpgκ°€ μ—†λ‹€λŠ” 점 μ™Έμ—λŠ” 그게 μ •ν™•νžˆ 무엇을 μ˜λ―Έν•˜λŠ”μ§€ λͺ¨λ₯΄κ² μŠ΅λ‹ˆλ‹€.

Dataset size: 10
Dataset of 10 instance(s)
Traceback (most recent call last):
  File "flow", line 6, in <module>
    cliHandler(sys.argv)
  File "/content/darkflow/darkflow/cli.py", line 33, in cliHandler
    print('Enter training ...'); tfnet.train()
  File "/content/darkflow/darkflow/net/flow.py", line 39, in train
    for i, (x_batch, datum) in enumerate(batches):
  File "/content/darkflow/darkflow/net/yolo/data.py", line 114, in shuffle
    inp, new_feed = self._batch(train_instance)
  File "/content/darkflow/darkflow/net/yolov2/data.py", line 28, in _batch
    img = self.preprocess(path, allobj)
  File "/content/darkflow/darkflow/net/yolo/predict.py", line 62, in preprocess
    result = imcv2_affine_trans(im)
  File "/content/darkflow/darkflow/utils/im_transform.py", line 20, in imcv2_affine_trans
    h, w, c = im.shape
AttributeError: 'NoneType' object has no attribute 'shape'

이 였λ₯˜κ°€ λ°œμƒν•˜λ©΄ ν•΄κ²° 방법 plz help

@wendq86 그것이 μž‘λ™ν•˜μ§€ μ•ŠλŠ” 것을 보면 - 경둜 없이 파일 이름을 넣어보고(예: <filename>000004.jpg</filename> ) ν›ˆλ ¨μ„ μ‹œλ„ν•  λ•Œ λ³€κ²½λ˜λŠ” 사항이 μžˆλŠ”μ§€ 확인할 수 μžˆμŠ΅λ‹ˆκΉŒ?

이것은 λ‚˜λ₯Ό μœ„ν•΄ μΌν–ˆμŠ΅λ‹ˆλ‹€

μ•ˆλ…•ν•˜μ„Έμš”, COCO 데이터 μ„ΈνŠΈλ₯Ό ν›ˆλ ¨ν•˜λ €κ³  ν•  λ•Œ λ™μΌν•œ λ¬Έμ œμ— μ§λ©΄ν–ˆμŠ΅λ‹ˆλ‹€. 이 문제λ₯Ό ν•΄κ²°ν•˜λŠ” 방법은 λ‹€μŒκ³Ό κ°™μŠ΅λ‹ˆλ‹€.

  1. https://github.com/tylin/coco-dpm/blob/master/coco/convert_to_pascalformat.py λ₯Ό μ‚¬μš©ν•˜μ—¬ COCO json ν˜•μ‹μ„ XML ν˜•μ‹μœΌλ‘œ λ³€ν™˜ν•©λ‹ˆλ‹€.

  2. κ·ΈλŸ¬λ‚˜ 이 μƒˆ XML 파일의 ν˜•μ‹μ΄ darkflow의 예제(darkflow/test/training/annotations)에 μžˆλŠ” VOC XML ν˜•μ‹κ³Ό λ™μΌν•˜λ„λ‘ 슀크립트의 일뢀λ₯Ό μˆ˜μ •ν•΄μ•Ό ν•©λ‹ˆλ‹€. 예λ₯Ό λ“€μ–΄:
    1단계 슀크립트의 COCO XML은 λ‹€μŒκ³Ό κ°™μŠ΅λ‹ˆλ‹€.
    <tag1>
    xxxxx
    </tag1>
    <tag2>
    xxxxx
    </tag2>
    κ·ΈλŸ¬λ‚˜ λ‹€μŒκ³Ό 같은 ν˜•μ‹μ΄ ν•„μš”ν•©λ‹ˆλ‹€.
    <tag1>xxxxx</tag>
    <tag2>xxxxx</tag2>

3 'label.txt' νŒŒμΌμ—μ„œ 'tvmonitor'λ₯Ό 'tv'둜 λ³€κ²½

λ‚˜λŠ” λͺ¨λ“  jpeg 이미지λ₯Ό μ‚­μ œν–ˆκ³  μž‘λ™ν–ˆμŠ΅λ‹ˆλ‹€

μ•ˆλ…•,

λ‚˜λŠ” μƒˆλ‘œμš΄ 데이터 μ„ΈνŠΈλ₯Ό ν›ˆλ ¨ν•˜κ³  μžˆμŠ΅λ‹ˆλ‹€. κ·ΈλŸ¬λ‚˜ ν›ˆλ ¨μ€ 항상 λͺ‡ 단계 λ™μ•ˆ μ‹€ν–‰λ˜λ©° κ°‘μžκΈ° λ‹€μŒ 였λ₯˜κ°€ λ°œμƒν•©λ‹ˆλ‹€. "AttributeError: 'NoneType' object has no attribute 'shape'". ꡐ윑이 λͺ‡ 단계 λ™μ•ˆ 싀행될 수 있고 μΆ”κ°€ 문제 ν•΄κ²° 방법에 λŒ€ν•œ 아이디어가 μ‹€ν–‰λ˜κ³  μžˆμœΌλ―€λ‘œ 주석 파일의 주석 ν˜•μ‹κ³Ό 파일 이름이 μ •ν™•ν•˜λ‹€κ³  μƒκ°ν•©λ‹ˆλ‹€.

이에 λŒ€ν•œ μ•„μ΄λ””μ–΄λ‚˜ 도움에 κ°μ‚¬λ“œλ¦½λ‹ˆλ‹€.

κ°μ‚¬ν•©λ‹ˆλ‹€.

root<strong i="10">@dd84391fd870</strong>:/ml/darkflow# flow --model cfg/tiny-yolo-new.cfg --train --dataset "../data/new/JPEGImages" --annotation "../data/new/Annotations"

Parsing cfg/tiny-yolo-new.cfg
Loading None ...
Finished in 0.00011324882507324219s

Building net ...
Source | Train? | Layer description                | Output size
-------+--------+----------------------------------+---------------
       |        | input                            | (?, 416, 416, 3)
 Init  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 416, 416, 16)
 Load  |  Yep!  | maxp 2x2p0_2                     | (?, 208, 208, 16)
 Init  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 208, 208, 32)
 Load  |  Yep!  | maxp 2x2p0_2                     | (?, 104, 104, 32)
 Init  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 104, 104, 64)
 Load  |  Yep!  | maxp 2x2p0_2                     | (?, 52, 52, 64)
 Init  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 52, 52, 128)
 Load  |  Yep!  | maxp 2x2p0_2                     | (?, 26, 26, 128)
 Init  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 26, 26, 256)
 Load  |  Yep!  | maxp 2x2p0_2                     | (?, 13, 13, 256)
 Init  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 13, 13, 512)
 Load  |  Yep!  | maxp 2x2p0_1                     | (?, 13, 13, 512)
 Init  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 13, 13, 1024)
 Init  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 13, 13, 1024)
 Init  |  Yep!  | conv 1x1p0_1    linear           | (?, 13, 13, 40)
-------+--------+----------------------------------+---------------
Running entirely on CPU
cfg/tiny-yolo-new.cfg loss hyper-parameters:
  H       = 13
  W       = 13
  box     = 5
  classes = 3
  scales  = [1.0, 5.0, 1.0, 1.0]
Building cfg/tiny-yolo-new.cfg loss
Building cfg/tiny-yolo-new.cfg train op
W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE3 instructions, but these are available on your machine and could speed up CPU computations.
W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
Finished in 7.207982778549194s

Enter training ...

cfg/tiny-yolo-new.cfg parsing ../data/new/Annotations
Parsing for ['tank', 'truck', 'apc'] 
[====================>]100%  000296.xml
Statistics:
apc: 48
tank: 70
truck: 24
Dataset size: 130
Dataset of 130 instance(s)
Training statistics: 
  Learning rate : 1e-05
  Batch size    : 16
  Epoch number  : 1000
  Backup every  : 2000
step 1 - loss 106.16172790527344 - moving ave loss 106.16172790527344
step 2 - loss 106.1773681640625 - moving ave loss 106.16329193115234
step 3 - loss 106.09341430664062 - moving ave loss 106.15630416870117
step 4 - loss 106.24054718017578 - moving ave loss 106.16472846984863
step 5 - loss 106.12216186523438 - moving ave loss 106.1604718093872
step 6 - loss 106.24075317382812 - moving ave loss 106.1684999458313
Traceback (most recent call last):
  File "/usr/local/bin/flow", line 6, in <module>
    cliHandler(sys.argv)
  File "/usr/local/lib/python3.5/dist-packages/darkflow/cli.py", line 29, in cliHandler
    print('Enter training ...'); tfnet.train()
  File "/usr/local/lib/python3.5/dist-packages/darkflow/net/flow.py", line 37, in train
    for i, (x_batch, datum) in enumerate(batches):
  File "/usr/local/lib/python3.5/dist-packages/darkflow/net/yolo/data.py", line 113, in shuffle
    inp, new_feed = self._batch(train_instance)
  File "/usr/local/lib/python3.5/dist-packages/darkflow/net/yolov2/data.py", line 27, in _batch
    img = self.preprocess(path, allobj)
  File "/usr/local/lib/python3.5/dist-packages/darkflow/net/yolo/predict.py", line 61, in preprocess
    result = imcv2_affine_trans(im)
  File "/usr/local/lib/python3.5/dist-packages/darkflow/utils/im_transform.py", line 19, in imcv2_affine_trans
    h, w, c = im.shape
AttributeError: 'NoneType' object has no attribute 'shape'

λͺ¨λ“  jpeg 이미지 μ‚­μ œ

μ•ˆλ…•ν•˜μ„Έμš”, μ €λŠ” μ‚¬μš©μž μ •μ˜ 개체 감지λ₯Ό ν›ˆλ ¨ν•˜μ—¬ νšŒμ‚¬ 둜고λ₯Ό κ°μ§€ν•˜λ €κ³  λ…Έλ ₯ν•˜κ³  μžˆμŠ΅λ‹ˆλ‹€. 이 였λ₯˜κ°€ λ°œμƒν•  λ•ŒκΉŒμ§€ λͺ¨λ“  것이 잘 μ§„ν–‰λ˜μ—ˆμŠ΅λ‹ˆλ‹€. λ˜ν•œ 이미지λ₯Ό λ‹€μ‹œ μ‚­μ œν•˜κ³  주석을 λ‹¬μ•˜μ§€λ§Œ κ²°κ³Όμ—λŠ” μ•„λ¬΄λŸ° λ³€ν™”κ°€ μ—†μ—ˆμŠ΅λ‹ˆλ‹€. λˆ„κ΅°κ°€ 이것을 λ„μ™€μ£Όμ„Έμš”.
감사 ν•΄μš”

(base) C:\Users\karanbari>cd Desktop/YOLO/darkflow-master

(base) C:\Users\karanbari\Desktop\YOLO\darkflow-master>python flow --model cfg/tiny-yolo-voc-1c.cfg --load bin/tiny-yolo-voc.weights --train --annotation annotations_clean --dataset images/train_clean --epoch 300
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\framework\dtypes.py:516: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint8 = np.dtype([("qint8", np.int8, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\framework\dtypes.py:517: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint8 = np.dtype([("quint8", np.uint8, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\framework\dtypes.py:518: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint16 = np.dtype([("qint16", np.int16, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\framework\dtypes.py:519: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint16 = np.dtype([("quint16", np.uint16, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\framework\dtypes.py:520: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint32 = np.dtype([("qint32", np.int32, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\framework\dtypes.py:525: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  np_resource = np.dtype([("resource", np.ubyte, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:541: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint8 = np.dtype([("qint8", np.int8, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:542: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint8 = np.dtype([("quint8", np.uint8, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:543: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint16 = np.dtype([("qint16", np.int16, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:544: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint16 = np.dtype([("quint16", np.uint16, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:545: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint32 = np.dtype([("qint32", np.int32, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:550: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  np_resource = np.dtype([("resource", np.ubyte, 1)])
WARNING: Logging before flag parsing goes to stderr.
W1124 18:22:27.201594 10144 deprecation_wrapper.py:119] From C:\Users\karanbari\Desktop\YOLO\darkflow-master\darkflow\net\build.py:15: The name tf.train.RMSPropOptimizer is deprecated. Please use tf.compat.v1.train.RMSPropOptimizer instead.

W1124 18:22:27.209591 10144 deprecation_wrapper.py:119] From C:\Users\karanbari\Desktop\YOLO\darkflow-master\darkflow\net\build.py:16: The name tf.train.AdadeltaOptimizer is deprecated. Please use tf.compat.v1.train.AdadeltaOptimizer instead.

W1124 18:22:27.209591 10144 deprecation_wrapper.py:119] From C:\Users\karanbari\Desktop\YOLO\darkflow-master\darkflow\net\build.py:17: The name tf.train.AdagradOptimizer is deprecated. Please use tf.compat.v1.train.AdagradOptimizer instead.

W1124 18:22:27.213590 10144 deprecation_wrapper.py:119] From C:\Users\karanbari\Desktop\YOLO\darkflow-master\darkflow\net\build.py:18: The name tf.train.AdagradDAOptimizer is deprecated. Please use tf.compat.v1.train.AdagradDAOptimizer instead.

W1124 18:22:27.213590 10144 deprecation_wrapper.py:119] From C:\Users\karanbari\Desktop\YOLO\darkflow-master\darkflow\net\build.py:19: The name tf.train.MomentumOptimizer is deprecated. Please use tf.compat.v1.train.MomentumOptimizer instead.


Parsing ./cfg/tiny-yolo-voc.cfg
Parsing cfg/tiny-yolo-voc-1c.cfg
Loading bin/tiny-yolo-voc.weights ...
Successfully identified 63471556 bytes
Finished in 0.019990205764770508s

Building net ...
W1124 18:22:27.253580 10144 deprecation_wrapper.py:119] From C:\Users\karanbari\Desktop\YOLO\darkflow-master\darkflow\net\build.py:105: The name tf.placeholder is deprecated. Please use tf.compat.v1.placeholder instead.

Source | Train? | Layer description                | Output size
-------+--------+----------------------------------+---------------
W1124 18:22:27.257580 10144 deprecation_wrapper.py:119] From C:\Users\karanbari\Desktop\YOLO\darkflow-master\darkflow\net\ops\baseop.py:70: The name tf.variable_scope is deprecated. Please use tf.compat.v1.variable_scope instead.

W1124 18:22:27.261598 10144 deprecation_wrapper.py:119] From C:\Users\karanbari\Desktop\YOLO\darkflow-master\darkflow\net\ops\baseop.py:71: The name tf.get_variable is deprecated. Please use tf.compat.v1.get_variable instead.

W1124 18:22:27.277594 10144 deprecation_wrapper.py:119] From C:\Users\karanbari\Desktop\YOLO\darkflow-master\darkflow\net\ops\baseop.py:84: The name tf.placeholder_with_default is deprecated. Please use tf.compat.v1.placeholder_with_default instead.

       |        | input                            | (?, 416, 416, 3)
 Load  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 416, 416, 16)
W1124 18:22:27.389549 10144 deprecation_wrapper.py:119] From C:\Users\karanbari\Desktop\YOLO\darkflow-master\darkflow\net\ops\simple.py:106: The name tf.nn.max_pool is deprecated. Please use tf.nn.max_pool2d instead.

 Load  |  Yep!  | maxp 2x2p0_2                     | (?, 208, 208, 16)
 Load  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 208, 208, 32)
 Load  |  Yep!  | maxp 2x2p0_2                     | (?, 104, 104, 32)
 Load  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 104, 104, 64)
 Load  |  Yep!  | maxp 2x2p0_2                     | (?, 52, 52, 64)
 Load  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 52, 52, 128)
 Load  |  Yep!  | maxp 2x2p0_2                     | (?, 26, 26, 128)
 Load  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 26, 26, 256)
 Load  |  Yep!  | maxp 2x2p0_2                     | (?, 13, 13, 256)
 Load  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 13, 13, 512)
 Load  |  Yep!  | maxp 2x2p0_1                     | (?, 13, 13, 512)
 Load  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 13, 13, 1024)
 Load  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 13, 13, 1024)
 Init  |  Yep!  | conv 1x1p0_1    linear           | (?, 13, 13, 30)
-------+--------+----------------------------------+---------------
Running entirely on CPU
cfg/tiny-yolo-voc-1c.cfg loss hyper-parameters:
        H       = 13
        W       = 13
        box     = 5
        classes = 1
        scales  = [1.0, 5.0, 1.0, 1.0]
W1124 18:22:29.962576 10144 deprecation.py:323] From C:\Users\karanbari\Desktop\YOLO\darkflow-master\darkflow\net\yolov2\train.py:87: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use `tf.cast` instead.
Building cfg/tiny-yolo-voc-1c.cfg loss
W1124 18:22:30.010835 10144 deprecation_wrapper.py:119] From C:\Users\karanbari\Desktop\YOLO\darkflow-master\darkflow\net\yolov2\train.py:107: The name tf.summary.scalar is deprecated. Please use tf.compat.v1.summary.scalar instead.

Building cfg/tiny-yolo-voc-1c.cfg train op
W1124 18:22:30.102793 10144 deprecation.py:323] From C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\ops\math_grad.py:1205: add_dispatch_support.<locals>.wrapper (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.where in 2.0, which has the same broadcast rule as np.where
W1124 18:22:32.038406 10144 deprecation.py:506] From C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\training\rmsprop.py:119: calling Ones.__init__ (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version.
Instructions for updating:
Call initializer instance with the dtype argument instead of passing it to the constructor
W1124 18:22:32.795700 10144 deprecation_wrapper.py:119] From C:\Users\karanbari\Desktop\YOLO\darkflow-master\darkflow\net\build.py:145: The name tf.Session is deprecated. Please use tf.compat.v1.Session instead.

2019-11-24 18:22:32.800843: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2
Finished in 11.774582862854004s

Enter training ...

cfg/tiny-yolo-voc-1c.cfg parsing annotations_clean
Parsing for ['vodafone']
[====================>]100%  Image9.xml
Statistics:
Dataset size: 53
Dataset of 53 instance(s)
Image20.jpg
Traceback (most recent call last):
  File "flow", line 6, in <module>
    cliHandler(sys.argv)
  File "C:\Users\karanbari\Desktop\YOLO\darkflow-master\darkflow\cli.py", line 33, in cliHandler
    print('Enter training ...'); tfnet.train()
  File "C:\Users\karanbari\Desktop\YOLO\darkflow-master\darkflow\net\flow.py", line 39, in train
    for i, (x_batch, datum) in enumerate(batches):
  File "C:\Users\karanbari\Desktop\YOLO\darkflow-master\darkflow\net\yolo\data.py", line 114, in shuffle
    inp, new_feed = self._batch(train_instance)
  File "C:\Users\karanbari\Desktop\YOLO\darkflow-master\darkflow\net\yolov2\data.py", line 28, in _batch
    img = self.preprocess(path, allobj)
  File "C:\Users\karanbari\Desktop\YOLO\darkflow-master\darkflow\net\yolo\predict.py", line 62, in preprocess
    result = imcv2_affine_trans(im)
  File "C:\Users\karanbari\Desktop\YOLO\darkflow-master\darkflow\utils\im_transform.py", line 20, in imcv2_affine_trans
    h, w, c = im.shape
AttributeError: 'NoneType' object has no attribute 'shape'

이미지 이름에 특수 λ¬Έμžκ°€ μžˆμŠ΅λ‹ˆκΉŒ? κ·Έλ ‡λ‹€λ©΄ λ³€κ²½ν•˜μ‹­μ‹œμ˜€.

2019λ…„ 11μ›” 24일 μΌμš”μΌ μ˜€ν›„ 6μ‹œ 32뢄에 karan bari [email protected] μ—μ„œ λ‹€μŒκ³Ό 같이 μΌμŠ΅λ‹ˆλ‹€.

μ•ˆλ…•ν•˜μ„Έμš”, μ €λŠ” μ‚¬μš©μž μ •μ˜ 개체 감지λ₯Ό ν›ˆλ ¨ν•˜μ—¬ λ‚΄
νšŒμ‚¬ 둜고,이 였λ₯˜κΉŒμ§€ λͺ¨λ“  것이 μž˜λ˜μ—ˆμŠ΅λ‹ˆλ‹€. λ‚˜λ„ μ‚­μ œν•˜κ³ 
이미지에 λ‹€μ‹œ 주석을 λ‹¬μ•˜μ§€λ§Œ κ²°κ³Όμ—λŠ” λ³€ν™”κ°€ μ—†μ—ˆμŠ΅λ‹ˆλ‹€. λˆ„κ΅°κ°€ 뢀탁해도 λ κΉŒμš”?
λ„μ™€μ€˜
감사 ν•΄μš”

(κΈ°λ³Έ) C:\Users\karanbari>cd Desktop/YOLO/darkflow-master

(κΈ°λ³Έ) C:\Users\karanbari\Desktop\YOLOdarkflow-master>python 흐름 --model cfg/tiny-yolo-voc-1c.cfg --load bin/tiny-yolo-voc.weights --train --annotation annotations_clean --dataset images/train_clean --epoch 300
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\frameworkdtypes.py:516: FutureWarning: (type, 1) λ˜λŠ” '1type'을 λ™μ˜μ–΄λ‘œ μ „λ‹¬ν•˜λŠ” 것은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. numpy의 ν–₯ν›„ λ²„μ „μ—μ„œλŠ” (type, (1,)) / '(1,)type'으둜 이해될 κ²ƒμž…λ‹ˆλ‹€.
_np_qint8 = np.dtype([("qint8", np.int8, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\frameworkdtypes.py:517: FutureWarning: (type, 1) λ˜λŠ” '1type'을 λ™μ˜μ–΄λ‘œ μ „λ‹¬ν•˜λŠ” 것은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. numpy의 ν–₯ν›„ λ²„μ „μ—μ„œλŠ” (type, (1,)) / '(1,)type'으둜 이해될 κ²ƒμž…λ‹ˆλ‹€.
_np_quint8 = np.dtype([("quint8", np.uint8, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\frameworkdtypes.py:518: FutureWarning: (type, 1) λ˜λŠ” '1type'을 λ™μ˜μ–΄λ‘œ μ „λ‹¬ν•˜λŠ” 것은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. numpy의 ν–₯ν›„ λ²„μ „μ—μ„œλŠ” (type, (1,)) / '(1,)type'으둜 이해될 κ²ƒμž…λ‹ˆλ‹€.
_np_qint16 = np.dtype([("qint16", np.int16, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\frameworkdtypes.py:519: FutureWarning: (type, 1) λ˜λŠ” '1type'을 λ™μ˜μ–΄λ‘œ μ „λ‹¬ν•˜λŠ” 것은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. numpy의 ν–₯ν›„ λ²„μ „μ—μ„œλŠ” (type, (1,)) / '(1,)type'으둜 이해될 κ²ƒμž…λ‹ˆλ‹€.
_np_quint16 = np.dtype([("quint16", np.uint16, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\frameworkdtypes.py:520: FutureWarning: (type, 1) λ˜λŠ” '1type'을 λ™μ˜μ–΄λ‘œ μ „λ‹¬ν•˜λŠ” 것은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. numpy의 ν–₯ν›„ λ²„μ „μ—μ„œλŠ” (type, (1,)) / '(1,)type'으둜 이해될 κ²ƒμž…λ‹ˆλ‹€.
_np_qint32 = np.dtype([("qint32", np.int32, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\frameworkdtypes.py:525: FutureWarning: (type, 1) λ˜λŠ” '1type'을 λ™μ˜μ–΄λ‘œ μ „λ‹¬ν•˜λŠ” 것은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. numpy의 ν–₯ν›„ λ²„μ „μ—μ„œλŠ” (type, (1,)) / '(1,)type'으둜 이해될 κ²ƒμž…λ‹ˆλ‹€.
np_resource = np.dtype([("λ¦¬μ†ŒμŠ€", np.ubyte, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorboard\compat\tensorflow_stubdtypes.py:541: FutureWarning: (type, 1) λ˜λŠ” '1type'을 λ™μ˜μ–΄λ‘œ μ „λ‹¬ν•˜λŠ” 것은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. numpy의 ν–₯ν›„ λ²„μ „μ—μ„œλŠ” (type, (1,)) / '(1,)type'으둜 이해될 κ²ƒμž…λ‹ˆλ‹€.
_np_qint8 = np.dtype([("qint8", np.int8, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorboard\compat\tensorflow_stubdtypes.py:542: FutureWarning: (type, 1) λ˜λŠ” '1type'을 λ™μ˜μ–΄λ‘œ μ „λ‹¬ν•˜λŠ” 것은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. numpy의 ν–₯ν›„ λ²„μ „μ—μ„œλŠ” (type, (1,)) / '(1,)type'으둜 이해될 κ²ƒμž…λ‹ˆλ‹€.
_np_quint8 = np.dtype([("quint8", np.uint8, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorboard\compat\tensorflow_stubdtypes.py:543: FutureWarning: (type, 1) λ˜λŠ” '1type'을 λ™μ˜μ–΄λ‘œ μ „λ‹¬ν•˜λŠ” 것은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. numpy의 ν–₯ν›„ λ²„μ „μ—μ„œλŠ” (type, (1,)) / '(1,)type'으둜 이해될 κ²ƒμž…λ‹ˆλ‹€.
_np_qint16 = np.dtype([("qint16", np.int16, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorboard\compat\tensorflow_stubdtypes.py:544: FutureWarning: (type, 1) λ˜λŠ” '1type'을 λ™μ˜μ–΄λ‘œ μ „λ‹¬ν•˜λŠ” 것은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. numpy의 ν–₯ν›„ λ²„μ „μ—μ„œλŠ” (type, (1,)) / '(1,)type'으둜 이해될 κ²ƒμž…λ‹ˆλ‹€.
_np_quint16 = np.dtype([("quint16", np.uint16, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorboard\compat\tensorflow_stubdtypes.py:545: FutureWarning: (type, 1) λ˜λŠ” '1type'을 λ™μ˜μ–΄λ‘œ μ „λ‹¬ν•˜λŠ” 것은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. numpy의 ν–₯ν›„ λ²„μ „μ—μ„œλŠ” (type, (1,)) / '(1,)type'으둜 이해될 κ²ƒμž…λ‹ˆλ‹€.
_np_qint32 = np.dtype([("qint32", np.int32, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorboard\compat\tensorflow_stubdtypes.py:550: FutureWarning: (type, 1) λ˜λŠ” '1type'을 λ™μ˜μ–΄λ‘œ μ „λ‹¬ν•˜λŠ” 것은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. numpy의 ν–₯ν›„ λ²„μ „μ—μ„œλŠ” (type, (1,)) / '(1,)type'으둜 이해될 κ²ƒμž…λ‹ˆλ‹€.
np_resource = np.dtype([("λ¦¬μ†ŒμŠ€", np.ubyte, 1)])
κ²½κ³ : ν”Œλž˜κ·Έ ꡬ문 뢄석 전에 λ‘œκΉ…μ€ stderr둜 μ΄λ™ν•©λ‹ˆλ‹€.
W1124 18:22:27.201594 10144 deprecation_wrapper.py:119] C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py:15μ—μ„œ: tf.train.RMSPropOptimizerλΌλŠ” 이름은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. λŒ€μ‹  tf.compat.v1.train.RMSPropOptimizerλ₯Ό μ‚¬μš©ν•˜μ‹­μ‹œμ˜€.

W1124 18:22:27.209591 10144 deprecation_wrapper.py:119] C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py:16μ—μ„œ: tf.train.AdadeltaOptimizerλΌλŠ” 이름은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. λŒ€μ‹  tf.compat.v1.train.AdadeltaOptimizerλ₯Ό μ‚¬μš©ν•˜μ‹­μ‹œμ˜€.

W1124 18:22:27.209591 10144 deprecation_wrapper.py:119] C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py:17μ—μ„œ: tf.train.AdagradOptimizerλΌλŠ” 이름은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. λŒ€μ‹  tf.compat.v1.train.AdagradOptimizerλ₯Ό μ‚¬μš©ν•˜μ‹­μ‹œμ˜€.

W1124 18:22:27.213590 10144 deprecation_wrapper.py:119] C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py:18μ—μ„œ: tf.train.AdagradDAOptimizerλΌλŠ” 이름은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. λŒ€μ‹  tf.compat.v1.train.AdagradDAOptimizerλ₯Ό μ‚¬μš©ν•˜μ‹­μ‹œμ˜€.

W1124 18:22:27.213590 10144 deprecation_wrapper.py:119] C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py:19μ—μ„œ: tf.train.MomentumOptimizerλΌλŠ” 이름은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. λŒ€μ‹  tf.compat.v1.train.MomentumOptimizerλ₯Ό μ‚¬μš©ν•˜μ‹­μ‹œμ˜€.

./cfg/tiny-yolo-voc.cfg ꡬ문 뢄석
cfg/tiny-yolo-voc-1c.cfg ꡬ문 뢄석
bin/tiny-yolo-voc.weights λ‘œλ“œ 쀑 ...
63471556λ°”μ΄νŠΈλ₯Ό μ„±κ³΅μ μœΌλ‘œ μ‹λ³„ν–ˆμŠ΅λ‹ˆλ‹€.
μ™„λ£Œ 0.019990205764770508s

ꡬ좕 κ·Έλ¬Ό ...
W1124 18:22:27.253580 10144 deprecation_wrapper.py:119] C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py:105μ—μ„œ: tf.placeholderλΌλŠ” 이름은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. λŒ€μ‹  tf.compat.v1.placeholderλ₯Ό μ‚¬μš©ν•˜μ„Έμš”.

좜처 | κΈ°μ°¨? | λ ˆμ΄μ–΄ μ„€λͺ… | 좜λ ₯ 크기
-------+--------+--------------------------------- -------------------
W1124 18:22:27.257580 10144 deprecation_wrapper.py:119] C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\ops\baseop.py:70μ—μ„œ: tf.variable_scopeλΌλŠ” 이름은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. λŒ€μ‹  tf.compat.v1.variable_scopeλ₯Ό μ‚¬μš©ν•˜μ„Έμš”.

W1124 18:22:27.261598 10144 deprecation_wrapper.py:119] C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\ops\baseop.py:71μ—μ„œ: tf.get_variable 이름은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. λŒ€μ‹  tf.compat.v1.get_variable을 μ‚¬μš©ν•˜μ‹­μ‹œμ˜€.

W1124 18:22:27.277594 10144 deprecation_wrapper.py:119] From C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\ops\baseop.py:84: tf.placeholder_with_defaultλΌλŠ” 이름은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. λŒ€μ‹  tf.compat.v1.placeholder_with_defaultλ₯Ό μ‚¬μš©ν•˜μ„Έμš”.

   |        | input                            | (?, 416, 416, 3)

λ‘œλ“œ | λ„€! | conv 3x3p1_1 +bnorm λˆ„μˆ˜ | (?, 416, 416, 16)
W1124 18:22:27.389549 10144 deprecation_wrapper.py:119] C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\ops\simple.py:106μ—μ„œ: tf.nn.max_poolμ΄λΌλŠ” 이름은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. λŒ€μ‹  tf.nn.max_pool2dλ₯Ό μ‚¬μš©ν•˜μ‹­μ‹œμ˜€.

λ‘œλ“œ | λ„€! | μ΅œλŒ€ 2x2p0_2 | (?, 208, 208, 16)
λ‘œλ“œ | λ„€! | conv 3x3p1_1 +bnorm λˆ„μˆ˜ | (?, 208, 208, 32)
λ‘œλ“œ | λ„€! | μ΅œλŒ€ 2x2p0_2 | (?, 104, 104, 32)
λ‘œλ“œ | λ„€! | conv 3x3p1_1 +bnorm λˆ„μˆ˜ | (?, 104, 104, 64)
λ‘œλ“œ | λ„€! | μ΅œλŒ€ 2x2p0_2 | (?, 52, 52, 64)
λ‘œλ“œ | λ„€! | conv 3x3p1_1 +bnorm λˆ„μˆ˜ | (?, 52, 52, 128)
λ‘œλ“œ | λ„€! | μ΅œλŒ€ 2x2p0_2 | (?, 26, 26, 128)
λ‘œλ“œ | λ„€! | conv 3x3p1_1 +bnorm λˆ„μˆ˜ | (?, 26, 26, 256)
λ‘œλ“œ | λ„€! | μ΅œλŒ€ 2x2p0_2 | (?, 13, 13, 256)
λ‘œλ“œ | λ„€! | conv 3x3p1_1 +bnorm λˆ„μˆ˜ | (?, 13, 13, 512)
λ‘œλ“œ | λ„€! | μ΅œλŒ€ 2x2p0_1 | (?, 13, 13, 512)
λ‘œλ“œ | λ„€! | conv 3x3p1_1 +bnorm λˆ„μˆ˜ | (?, 13, 13, 1024)
λ‘œλ“œ | λ„€! | conv 3x3p1_1 +bnorm λˆ„μˆ˜ | (?, 13, 13, 1024)
μ΄ˆκΈ°ν™” | λ„€! | λ³€ν™˜ 1x1p0_1 μ„ ν˜• | (?, 13, 13, 30)
-------+--------+--------------------------------- -------------------
CPUμ—μ„œ μ™„μ „νžˆ μ‹€ν–‰
cfg/tiny-yolo-voc-1c.cfg 손싀 ν•˜μ΄νΌ λ§€κ°œλ³€μˆ˜:
H = 13
승 = 13
μƒμž = 5
클래슀 = 1
척도 = [1.0, 5.0, 1.0, 1.0]
W1124 18:22:29.962576 10144 deprecation.py:323] From C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\yolov2\train.py:87: to_float (tensorflow.python.opsedμ—μ„œ) is deprethon.ma ν–₯ν›„ λ²„μ „μ—μ„œ μ œκ±°λ©λ‹ˆλ‹€.
μ—…λ°μ΄νŠΈ 지침:
λŒ€μ‹  tf.cast λ₯Ό μ‚¬μš©ν•˜μ‹­μ‹œμ˜€.
cfg/tiny-yolo-voc-1c.cfg 손싀 ꡬ좕
W1124 18:22:30.010835 10144 deprecation_wrapper.py:119] C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\yolov2\train.py:107μ—μ„œ: tf.summary.scalarλΌλŠ” 이름은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. λŒ€μ‹  tf.compat.v1.summary.scalarλ₯Ό μ‚¬μš©ν•˜μ‹­μ‹œμ˜€.

건물 cfg/tiny-yolo-voc-1c.cfg κΈ°μ°¨ μž‘μ—…
W1124 18:22:30.102793 10144 deprecation.py:323] C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\ops\math_grad.py:1205: add_dispatch_supportμ—μ„œ..wrapper(tensorflow.python.ops.array_opsμ—μ„œ)λŠ” 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμœΌλ©° ν–₯ν›„ λ²„μ „μ—μ„œ μ œκ±°λ©λ‹ˆλ‹€.
μ—…λ°μ΄νŠΈ 지침:
np.where와 λΈŒλ‘œλ“œμΊμŠ€νŠΈ κ·œμΉ™μ΄ λ™μΌν•œ 2.0μ—μ„œ tf.whereλ₯Ό μ‚¬μš©ν•©λ‹ˆλ‹€.
W1124 18:22:32.038406 10144 deprecation.py:506] From C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\training\rmsprop.py:119: Ones.__init__ 호좜(ν…μ„œν”Œλ‘œμš°μ—μ„œ .ops.init_ops) dtype을 μ‚¬μš©ν•˜λŠ” 것은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμœΌλ©° ν–₯ν›„ λ²„μ „μ—μ„œ μ œκ±°λ©λ‹ˆλ‹€.
μ—…λ°μ΄νŠΈ 지침:
μƒμ„±μžμ— μ „λ‹¬ν•˜λŠ” λŒ€μ‹  dtype 인수λ₯Ό μ‚¬μš©ν•˜μ—¬ μ΄ˆκΈ°ν™” μΈμŠ€ν„΄μŠ€λ₯Ό ν˜ΈμΆœν•©λ‹ˆλ‹€.
W1124 18:22:32.795700 10144 deprecation_wrapper.py:119] C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py:145μ—μ„œ: tf.Sessionμ΄λΌλŠ” 이름은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. λŒ€μ‹  tf.compat.v1.Session을 μ‚¬μš©ν•˜μ‹­μ‹œμ˜€.

2019-11-24 18:22:32.800843: I tensorflow/core/platform/cpu_feature_guard.cc:142] κ·€ν•˜μ˜ CPUλŠ” 이 TensorFlow λ°”μ΄λ„ˆλ¦¬κ°€ μ‚¬μš©ν•˜λ„λ‘ μ»΄νŒŒμΌλ˜μ§€ μ•Šμ€ λͺ…령을 μ§€μ›ν•©λ‹ˆλ‹€: AVX2
11.774582862854004sμ—μ„œ μ™„λ£Œ

ν›ˆλ ¨μ— λ“€μ–΄κ°€λ‹€ ...

cfg/tiny-yolo-voc-1c.cfg 주석 ꡬ문 뢄석
['보닀폰'] ꡬ문 뢄석
[=====================>]100% Image9.xml
톡계:
데이터 μ„ΈνŠΈ 크기: 53
53개 μΈμŠ€ν„΄μŠ€μ˜ λ°μ΄ν„°μ„ΈνŠΈ
이미지20.jpg
역좔적(κ°€μž₯ 졜근 호좜 λ§ˆμ§€λ§‰):
파일 "흐름", 6ν–‰,
cliHandler(sys.argv)
파일 "C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\cli.py", 33ν–‰, cliHandler
print('ν›ˆλ ¨ μž…λ ₯...'); tfnet.train()
파일 "C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\flow.py", 39ν–‰, κΈ°μ°¨
enumerate(batch)의 i, (x_batch, datum):
파일 "C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\yolodata.py", 114ν–‰, μ…”ν”Œ
inp, new_feed = self._batch(train_instance)
파일 "C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\yolov2data.py", 28ν–‰, _batch
img = self.preprocess(경둜, allobj)
파일 "C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\yolo\predict.py", 62ν–‰, μ „μ²˜λ¦¬ 쀑
κ²°κ³Ό = imcv2_affine_trans(im)
imcv2_affine_trans의 파일 "C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflowutils\im_transform.py", 20ν–‰
h, w, c = im.shape
AttributeError: 'NoneType' κ°œμ²΄μ— 'shape' 속성이 μ—†μŠ΅λ‹ˆλ‹€.

β€”
당신이 λŒ“κΈ€μ„ λ‹¬μ•˜κΈ° λ•Œλ¬Έμ— 이것을 λ°›λŠ” κ²ƒμž…λ‹ˆλ‹€.
이 이메일에 직접 λ‹΅μž₯ν•˜κ³  GitHubμ—μ„œ ν™•μΈν•˜μ„Έμš”.
https://github.com/thtrieu/darkflow/issues/265?email_source=notifications&email_token=AGG23MNSSXWIHQFI75KYEWDQVJ3ORA5CNFSM4DNJVSV2YY3PNVWWK3TUL52HS4DFVEXG43VMVBW63LN
λ˜λŠ” ꡬ독 μ·¨μ†Œ
https://github.com/notifications/unsubscribe-auth/AGG23MMETFBN5NG76IHGWZ3QVJ3ORANCNFSM4DNJVSVQ
.

이미지 이름에 특수 λ¬Έμžκ°€ μžˆμŠ΅λ‹ˆκΉŒ? κ·Έλ ‡λ‹€λ©΄ λ³€κ²½ν•˜μ‹­μ‹œμ˜€.
…
2019λ…„ 11μ›” 24일 μΌμš”μΌ μ˜€ν›„ 6μ‹œ 32λΆ„, karan bari @ . * > μž‘μ„±: μ•ˆλ…•ν•˜μ„Έμš”, μ €λŠ” νšŒμ‚¬ 둜고λ₯Ό κ°μ§€ν•˜κΈ° μœ„ν•΄ μ‚¬μš©μž 지정 개체 감지λ₯Ό ν›ˆλ ¨ν•˜λ €κ³  ν•©λ‹ˆλ‹€. 이 였λ₯˜κ°€ λ°œμƒν•  λ•ŒκΉŒμ§€ λͺ¨λ“  것이 잘 μ§„ν–‰λ˜μ—ˆμŠ΅λ‹ˆλ‹€. λ˜ν•œ 이미지λ₯Ό λ‹€μ‹œ μ‚­μ œν•˜κ³  주석을 λ‹¬μ•˜μ§€λ§Œ κ²°κ³Όμ—λŠ” λ³€ν™”κ°€ μ—†μ—ˆμŠ΅λ‹ˆλ‹€. λˆ„κ΅°κ°€ 이 μž‘μ—…μ„ 도와쀄 수 μžˆμŠ΅λ‹ˆκΉŒ? κ°μ‚¬ν•©λ‹ˆλ‹€(κΈ°λ³Έ) C:\Users\karanbari>cd Desktop/YOLO/darkflow-master(κΈ°λ³Έ) C:\Users\karanbari\Desktop\YOLOdarkflow-master>python flow --model cfg/ tiny-yolo-voc-1c.cfg --load bin/tiny-yolo-voc.weights --train --annotation annotations_clean --dataset images/train_clean --epoch 300 C:\Users\karanbari\Anaconda3\lib\site -packages\tensorflow\python\frameworkdtypes.py:516: FutureWarning: (type, 1) λ˜λŠ” '1type'을 λ™μ˜μ–΄λ‘œ μ „λ‹¬ν•˜λŠ” 것은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. numpy의 ν–₯ν›„ λ²„μ „μ—μ„œλŠ” (type, (1,)) / '(1,)type'으둜 이해될 κ²ƒμž…λ‹ˆλ‹€. _np_qint8 = np.dtype([("qint8", np.int8, 1)]) C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\frameworkdtypes.py:517: FutureWarning: 톡과(μœ ν˜• , 1) μœ ν˜•μ˜ λ™μ˜μ–΄μΈ '1type'은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. numpy의 ν–₯ν›„ λ²„μ „μ—μ„œλŠ” (type, (1,)) / '(1,)type'으둜 이해될 κ²ƒμž…λ‹ˆλ‹€. _np_quint8 = np.dtype([("quint8", np.uint8, 1)]) C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\frameworkdtypes.py:518: FutureWarning: 톡과(μœ ν˜• , 1) μœ ν˜•μ˜ λ™μ˜μ–΄μΈ '1type'은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. numpy의 ν–₯ν›„ λ²„μ „μ—μ„œλŠ” (type, (1,)) / '(1,)type'으둜 이해될 κ²ƒμž…λ‹ˆλ‹€. _np_qint16 = np.dtype([("qint16", np.int16, 1)]) C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\frameworkdtypes.py:519: FutureWarning: 톡과(μœ ν˜• , 1) μœ ν˜•μ˜ λ™μ˜μ–΄μΈ '1type'은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. numpy의 ν–₯ν›„ λ²„μ „μ—μ„œλŠ” (type, (1,)) / '(1,)type'으둜 이해될 κ²ƒμž…λ‹ˆλ‹€. _np_quint16 = np.dtype([("quint16", np.uint16, 1)]) C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\frameworkdtypes.py:520: FutureWarning: 톡과(μœ ν˜• , 1) μœ ν˜•μ˜ λ™μ˜μ–΄μΈ '1type'은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. numpy의 ν–₯ν›„ λ²„μ „μ—μ„œλŠ” (type, (1,)) / '(1,)type'으둜 이해될 κ²ƒμž…λ‹ˆλ‹€. _np_qint32 = np.dtype([("qint32", np.int32, 1)]) C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\frameworkdtypes.py:525: FutureWarning: 톡과(μœ ν˜• , 1) μœ ν˜•μ˜ λ™μ˜μ–΄μΈ '1type'은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. numpy의 ν–₯ν›„ λ²„μ „μ—μ„œλŠ” (type, (1,)) / '(1,)type'으둜 이해될 κ²ƒμž…λ‹ˆλ‹€. np_resource = np.dtype([("resource", np.ubyte, 1)]) C:\Users\karanbari\Anaconda3\lib\site-packages\tensorboard\compat\tensorflow_stubdtypes.py:541: FutureWarning: 톡과(μœ ν˜• , 1) μœ ν˜•μ˜ λ™μ˜μ–΄μΈ '1type'은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. numpy의 ν–₯ν›„ λ²„μ „μ—μ„œλŠ” (type, (1,)) / '(1,)type'으둜 이해될 κ²ƒμž…λ‹ˆλ‹€. _np_qint8 = np.dtype([("qint8", np.int8, 1)]) C:\Users\karanbari\Anaconda3\lib\site-packages\tensorboard\compat\tensorflow_stubdtypes.py:542: FutureWarning: 톡과(μœ ν˜• , 1) μœ ν˜•μ˜ λ™μ˜μ–΄μΈ '1type'은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. numpy의 ν–₯ν›„ λ²„μ „μ—μ„œλŠ” (type, (1,)) / '(1,)type'으둜 이해될 κ²ƒμž…λ‹ˆλ‹€. _np_quint8 = np.dtype([("quint8", np.uint8, 1)]) C:\Users\karanbari\Anaconda3\lib\site-packages\tensorboard\compat\tensorflow_stubdtypes.py:543: FutureWarning: 톡과(μœ ν˜• , 1) μœ ν˜•μ˜ λ™μ˜μ–΄μΈ '1type'은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. numpy의 ν–₯ν›„ λ²„μ „μ—μ„œλŠ” (type, (1,)) / '(1,)type'으둜 이해될 κ²ƒμž…λ‹ˆλ‹€. _np_qint16 = np.dtype([("qint16", np.int16, 1)]) C:\Users\karanbari\Anaconda3\lib\site-packages\tensorboard\compat\tensorflow_stubdtypes.py:544: FutureWarning: 톡과(μœ ν˜• , 1) μœ ν˜•μ˜ λ™μ˜μ–΄μΈ '1type'은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. numpy의 ν–₯ν›„ λ²„μ „μ—μ„œλŠ” (type, (1,)) / '(1,)type'으둜 이해될 κ²ƒμž…λ‹ˆλ‹€. _np_quint16 = np.dtype([("quint16", np.uint16, 1)]) C:\Users\karanbari\Anaconda3\lib\site-packages\tensorboard\compat\tensorflow_stubdtypes.py:545: FutureWarning: 톡과(μœ ν˜• , 1) μœ ν˜•μ˜ λ™μ˜μ–΄μΈ '1type'은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. numpy의 ν–₯ν›„ λ²„μ „μ—μ„œλŠ” (type, (1,)) / '(1,)type'으둜 이해될 κ²ƒμž…λ‹ˆλ‹€. _np_qint32 = np.dtype([("qint32", np.int32, 1)]) C:\Users\karanbari\Anaconda3\lib\site-packages\tensorboard\compat\tensorflow_stubdtypes.py:550: FutureWarning: 톡과(μœ ν˜• , 1) μœ ν˜•μ˜ λ™μ˜μ–΄μΈ '1type'은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. numpy의 ν–₯ν›„ λ²„μ „μ—μ„œλŠ” (type, (1,)) / '(1,)type'으둜 이해될 κ²ƒμž…λ‹ˆλ‹€. np_resource = np.dtype([("resource", np.ubyte, 1)]) κ²½κ³ : ν”Œλž˜κ·Έ ꡬ문 뢄석 μ „μ˜ λ‘œκΉ…μ€ stderr둜 μ΄λ™ν•©λ‹ˆλ‹€. W1124 18:22:27.201594 10144 deprecation_wrapper.py:119] C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py:15μ—μ„œ: tf.train.RMSPropOptimizerλΌλŠ” 이름은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. λŒ€μ‹  tf.compat.v1.train.RMSPropOptimizerλ₯Ό μ‚¬μš©ν•˜μ‹­μ‹œμ˜€. W1124 18:22:27.209591 10144 deprecation_wrapper.py:119] C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py:16μ—μ„œ: tf.train.AdadeltaOptimizerλΌλŠ” 이름은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. λŒ€μ‹  tf.compat.v1.train.AdadeltaOptimizerλ₯Ό μ‚¬μš©ν•˜μ‹­μ‹œμ˜€. W1124 18:22:27.209591 10144 deprecation_wrapper.py:119] C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py:17μ—μ„œ: tf.train.AdagradOptimizerλΌλŠ” 이름은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. λŒ€μ‹  tf.compat.v1.train.AdagradOptimizerλ₯Ό μ‚¬μš©ν•˜μ‹­μ‹œμ˜€. W1124 18:22:27.213590 10144 deprecation_wrapper.py:119] C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py:18μ—μ„œ: tf.train.AdagradDAOptimizerλΌλŠ” 이름은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. λŒ€μ‹  tf.compat.v1.train.AdagradDAOptimizerλ₯Ό μ‚¬μš©ν•˜μ‹­μ‹œμ˜€. W1124 18:22:27.213590 10144 deprecation_wrapper.py:119] C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py:19μ—μ„œ: tf.train.MomentumOptimizerλΌλŠ” 이름은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. λŒ€μ‹  tf.compat.v1.train.MomentumOptimizerλ₯Ό μ‚¬μš©ν•˜μ‹­μ‹œμ˜€. Parsing ./cfg/tiny-yolo-voc.cfg Parsing cfg/tiny-yolo-voc-1c.cfg Loading bin/tiny-yolo-voc.weights ... 63471556 λ°”μ΄νŠΈλ₯Ό μ„±κ³΅μ μœΌλ‘œ μ‹λ³„ν–ˆμŠ΅λ‹ˆλ‹€ 0.019990205764770508s λΉŒλ”© λ„€νŠΈ W1124 18:22:27.253580 10144 deprecation_wrapper.py:119] C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py:105μ—μ„œ: tf.placeholderλΌλŠ” 이름은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. λŒ€μ‹  tf.compat.v1.placeholderλ₯Ό μ‚¬μš©ν•˜μ„Έμš”. 좜처 | κΈ°μ°¨? | λ ˆμ΄μ–΄ μ„€λͺ… | 좜λ ₯ 크기 -------+--------+------------------------------ ---+------------ W1124 18:22:27.257580 10144 deprecation_wrapper.py:119] C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\ops\μ—μ„œ baseop.py:70: tf.variable_scopeλΌλŠ” 이름은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. λŒ€μ‹  tf.compat.v1.variable_scopeλ₯Ό μ‚¬μš©ν•˜μ„Έμš”. W1124 18:22:27.261598 10144 deprecation_wrapper.py:119] C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\ops\baseop.py:71μ—μ„œ: tf.get_variable 이름은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. λŒ€μ‹  tf.compat.v1.get_variable을 μ‚¬μš©ν•˜μ‹­μ‹œμ˜€. W1124 18:22:27.277594 10144 deprecation_wrapper.py:119] From C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\ops\baseop.py:84: tf.placeholder_with_defaultλΌλŠ” 이름은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. λŒ€μ‹  tf.compat.v1.placeholder_with_defaultλ₯Ό μ‚¬μš©ν•˜μ„Έμš”. | | μž…λ ₯ | (?, 416, 416, 3) λ‘œλ“œ | λ„€! | conv 3x3p1_1 +bnorm λˆ„μˆ˜ | (?, 416, 416, 16) W1124 18:22:27.389549 10144 deprecation_wrapper.py:119] C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\ops\simple.py:10μ—μ„œ nn.max_pool은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. λŒ€μ‹  tf.nn.max_pool2dλ₯Ό μ‚¬μš©ν•˜μ‹­μ‹œμ˜€. λ‘œλ“œ | λ„€! | μ΅œλŒ€ 2x2p0_2 | (?, 208, 208, 16) λ‘œλ“œ | λ„€! | conv 3x3p1_1 +bnorm λˆ„μˆ˜ | (?, 208, 208, 32) λ‘œλ“œ | λ„€! | μ΅œλŒ€ 2x2p0_2 | (?, 104, 104, 32) λ‘œλ“œ | λ„€! | conv 3x3p1_1 +bnorm λˆ„μˆ˜ | (?, 104, 104, 64) λ‘œλ“œ | λ„€! | μ΅œλŒ€ 2x2p0_2 | (?, 52, 52, 64) λ‘œλ“œ | λ„€! | conv 3x3p1_1 +bnorm λˆ„μˆ˜ | (?, 52, 52, 128) λ‘œλ“œ | λ„€! | μ΅œλŒ€ 2x2p0_2 | (?, 26, 26, 128) λ‘œλ“œ | λ„€! | conv 3x3p1_1 +bnorm λˆ„μˆ˜ | (?, 26, 26, 256) λ‘œλ“œ | λ„€! | μ΅œλŒ€ 2x2p0_2 | (?, 13, 13, 256) λ‘œλ“œ | λ„€! | conv 3x3p1_1 +bnorm λˆ„μˆ˜ | (?, 13, 13, 512) λ‘œλ“œ | λ„€! | μ΅œλŒ€ 2x2p0_1 | (?, 13, 13, 512) λ‘œλ“œ | λ„€! | conv 3x3p1_1 +bnorm λˆ„μˆ˜ | (?, 13, 13, 1024) λ‘œλ“œ | λ„€! | conv 3x3p1_1 +bnorm λˆ„μˆ˜ | (?, 13, 13, 1024) μ΄ˆκΈ°ν™” | λ„€! | λ³€ν™˜ 1x1p0_1 μ„ ν˜• | (?, 13, 13, 30) -------+--------+------------------------ ----------+--------------- CPUμ—μ„œ μ™„μ „νžˆ μ‹€ν–‰ cfg/tiny-yolo-voc-1c.cfg 손싀 ν•˜μ΄νΌ λ§€κ°œλ³€μˆ˜: H = 13 W = 13 μƒμž = 5 클래슀 = 1 μŠ€μΌ€μΌ = [1.0, 5.0, 1.0, 1.0] W1124 18:22:29.962576 10144 deprecation.py:323] C:\Users\karanbari\Desktop\YOLOdarkflow\net\yolovflow\net\yolovflowμ—μ„œ train.py:87: to_float(tensorflow.python.ops.math_opsμ—μ„œ)λŠ” 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμœΌλ©° ν–₯ν›„ λ²„μ „μ—μ„œ μ œκ±°λ©λ‹ˆλ‹€. μ—…λ°μ΄νŠΈ 지침: λŒ€μ‹  tf.cast λ₯Ό μ‚¬μš©ν•˜μ„Έμš”. Building cfg/tiny-yolo-voc-1c.cfg loss W1124 18:22:30.010835 10144 deprecation_wrapper.py:119] From C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\yolov107\train.py: tf.summary.scalarλΌλŠ” 이름은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. λŒ€μ‹  tf.compat.v1.summary.scalarλ₯Ό μ‚¬μš©ν•˜μ‹­μ‹œμ˜€. Building cfg/tiny-yolo-voc-1c.cfg train op W1124 18:22:30.102793 10144 deprecation.py:323] From C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\ops\math_grad .py:1205: add_dispatch_support..wrapper(tensorflow.python.ops.array_opsμ—μ„œ)λŠ” 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμœΌλ©° ν–₯ν›„ λ²„μ „μ—μ„œ μ œκ±°λ©λ‹ˆλ‹€. μ—…λ°μ΄νŠΈ 지침: np.where W1124 18:22:32.038406 10144 deprecation.py:506] λΈŒλ‘œλ“œμΊμŠ€νŠΈ κ·œμΉ™μ΄ λ™μΌν•œ 2.0의 tf.whereλ₯Ό μ‚¬μš©ν•˜μ„Έμš”. From C:\Users\karanbari\Anaconda3\lib\site-packages\ tensorflow\python\training\rmsprop.py:119: dtype을 μ‚¬μš©ν•˜μ—¬ Ones.__init__(tensorflow.python.ops.init_opsμ—μ„œ) ν˜ΈμΆœμ€ 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμœΌλ©° ν–₯ν›„ λ²„μ „μ—μ„œ μ œκ±°λ©λ‹ˆλ‹€. μ—…λ°μ΄νŠΈ 지침: μƒμ„±μžμ— μ „λ‹¬ν•˜λŠ” λŒ€μ‹  dtype 인수둜 μ΄ˆκΈ°ν™” μΈμŠ€ν„΄μŠ€λ₯Ό ν˜ΈμΆœν•©λ‹ˆλ‹€. W1124 18:22:32.795700 10144 deprecation_wrapper.py:119] From C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py :145: tf.Sessionμ΄λΌλŠ” 이름은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. λŒ€μ‹  tf.compat.v1.Session을 μ‚¬μš©ν•˜μ‹­μ‹œμ˜€. 2019-11-24 18:22:32.800843: I tensorflow/core/platform/cpu_feature_guard.cc:142] κ·€ν•˜μ˜ CPUλŠ” 이 TensorFlow λ°”μ΄λ„ˆλ¦¬κ°€ μ‚¬μš©ν•˜λ„λ‘ μ»΄νŒŒμΌλ˜μ§€ μ•Šμ•˜λ‹€λŠ” λͺ…령을 μ§€μ›ν•©λ‹ˆλ‹€. AVX2 Finished in 11.774582862854004cfg Enter training tiny-yolo-voc-1c.cfg parsing annotations_clean ['vodafone']에 λŒ€ν•œ ꡬ문 뢄석 [===================>]100% Image9.xml 톡계: 데이터 μ„ΈνŠΈ 크기 : 53개 μΈμŠ€ν„΄μŠ€μ˜ 53개 데이터 μ„ΈνŠΈ Image20.jpg 역좔적(κ°€μž₯ 졜근 호좜 λ§ˆμ§€λ§‰): 파일 "flow", 쀄 6, incliHandler(sys.argv) 파일 "C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\cli.py", 33ν–‰, cliHandlerμ—μ„œ print('Enter training ...'); tfnet.train() 파일 "C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\flow.py", 쀄 39, i에 λŒ€ν•œ κΈ°μ°¨, (x_batch, datum) in enumerate(배치): 파일 "C: \Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\yolodata.py", 114ν–‰, μ…”ν”Œ inp, new_feed = self._batch(train_instance) 파일 "C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\ yolov2data.py", 28ν–‰, _batch img = self.preprocess(path, allobj) 파일 "C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\yolo\predict.py", 62ν–‰, μ „μ²˜λ¦¬ κ²°κ³Ό = imcv2_affine_trans(im) 파일 "C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflowutils\im_transform.py", 20ν–‰, imcv2_affine_trans h, w, c = im.shape AttributeError: 'NoneType' κ°œμ²΄μ— 'shape' 속성이 μ—†μŠ΅λ‹ˆλ‹€. ' β€” 당신이 λŒ“κΈ€μ„ λ‹¬μ•˜κΈ° λ•Œλ¬Έμ— 이것을 λ°›λŠ” κ²ƒμž…λ‹ˆλ‹€. λ°”λ‘œμ΄ 이메일에 νšŒμ‹  GitHubμ˜μ—μ„œ λ³Ό <# 265? email_source = 톡지 및 email_token = AGG23MNSSXWIHQFI75KYEWDQVJ3ORA5CNFSM4DNJVSV2YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOEFAKXNA # issuecomment-557886388>, λ˜λŠ” ꡬ독 μ·¨μ†Œ https://github.com/notifications/unsubscribe-auth/AGG23MMETFBN5NG76IHGWZ3QVJ3ORANCNFSM4DNJVSVQ .

μ•„λ‹ˆμš”, Image1, Image2, Image3... λ“± ν˜•μ‹μ˜ λͺ¨λ“  이미지λ₯Ό μž¬μ •μ˜ν–ˆμœΌλ©° λͺ¨λ“  μ΄λ―Έμ§€μ˜ ν˜•μ‹μ€ .jpgμž…λ‹ˆλ‹€.

주석 치수 쀑 ν•˜λ‚˜κ°€ λ‹€μŒλ³΄λ‹€ μž‘μ„ κ°€λŠ₯성이 맀우 λ†’μŠ΅λ‹ˆλ‹€.
0 λ˜λŠ” μ΄λ―Έμ§€μ—μ„œ λ²—μ–΄λ‚¬μŠ΅λ‹ˆλ‹€.

λ˜ν•œ λͺ¨λ“  이미지λ₯Ό μˆ˜λ™μœΌλ‘œ μ—΄ 수 μžˆλŠ”μ§€ ν™•μΈν•˜μ‹­μ‹œμ˜€.

2019λ…„ 11μ›” 24일 μΌμš”μΌ μ˜€ν›„ 6μ‹œ 42뢄에 karan bari [email protected] μ—μ„œ λ‹€μŒκ³Ό 같이 μΌμŠ΅λ‹ˆλ‹€.

이미지 이름에 특수 λ¬Έμžκ°€ μžˆμŠ΅λ‹ˆκΉŒ? κ·Έλ ‡λ‹€λ©΄ λ³€κ²½ν•˜μ‹­μ‹œμ˜€.
… <#m_-6851739743886041955_>
2019λ…„ 11μ›” 24일 μΌμš”μΌ μ˜€ν›„ 6μ‹œ 32λΆ„, karan bari @ . * > μ“΄: μ•ˆλ…•ν•˜μ„Έμš”, μ €λŠ”
λ‚΄ νšŒμ‚¬ 둜고λ₯Ό κ°μ§€ν•˜κΈ° μœ„ν•΄ μ‚¬μš©μž μ •μ˜ 개체 감지λ₯Ό ν›ˆλ ¨ν•˜λ €κ³  μ‹œλ„ν•©λ‹ˆλ‹€.
이 였λ₯˜κΉŒμ§€ λͺ¨λ“  것이 잘 μ§„ν–‰λ˜μ—ˆμœΌλ©° 이미지도 μ‚­μ œν•˜κ³  주석을 λ‹¬μ•˜μŠ΅λ‹ˆλ‹€.
λ‹€μ‹œ λ§ν•˜μ§€λ§Œ κ²°κ³Όμ—λŠ” λ³€ν™”κ°€ μ—†μŠ΅λ‹ˆλ‹€. λˆ„κ΅°κ°€ 이것을 λ„μ™€μ£Όμ„Έμš”.
κ°μ‚¬ν•©λ‹ˆλ‹€(κΈ°λ³Έ) C:\Users\karanbari>cd Desktop/YOLO/darkflow-master(κΈ°λ³Έ)
C:\Users\karanbari\Desktop\YOLOdarkflow-master>python 흐름 --λͺ¨λΈ
cfg/tiny-yolo-voc-1c.cfg --load bin/tiny-yolo-voc.weights --train
--annotation annotations_clean --dataset images/train_clean --epoch 300
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\frameworkdtypes.py:516:
FutureWarning: (type, 1) λ˜λŠ” '1type'을 type의 λ™μ˜μ–΄λ‘œ μ „λ‹¬ν•˜λ©΄
더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŒ numpy의 ν–₯ν›„ λ²„μ „μ—μ„œλŠ” (μœ ν˜•,
(1,)) / '(1,)μœ ν˜•'. _np_qint8 = np.dtype([("qint8", np.int8, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\frameworkdtypes.py:517:
FutureWarning: (type, 1) λ˜λŠ” '1type'을 type의 λ™μ˜μ–΄λ‘œ μ „λ‹¬ν•˜λ©΄
더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŒ numpy의 ν–₯ν›„ λ²„μ „μ—μ„œλŠ” (μœ ν˜•,
(1,)) / '(1,)μœ ν˜•'. _np_quint8 = np.dtype([("quint8", np.uint8, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\frameworkdtypes.py:518:
FutureWarning: (type, 1) λ˜λŠ” '1type'을 type의 λ™μ˜μ–΄λ‘œ μ „λ‹¬ν•˜λ©΄
더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŒ numpy의 ν–₯ν›„ λ²„μ „μ—μ„œλŠ” (μœ ν˜•,
(1,)) / '(1,)μœ ν˜•'. _np_qint16 = np.dtype([("qint16", np.int16, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\frameworkdtypes.py:519:
FutureWarning: (type, 1) λ˜λŠ” '1type'을 type의 λ™μ˜μ–΄λ‘œ μ „λ‹¬ν•˜λ©΄
더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŒ numpy의 ν–₯ν›„ λ²„μ „μ—μ„œλŠ” (μœ ν˜•,
(1,)) / '(1,)μœ ν˜•'. _np_quint16 = np.dtype([("quint16", np.uint16, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\frameworkdtypes.py:520:
FutureWarning: (type, 1) λ˜λŠ” '1type'을 type의 λ™μ˜μ–΄λ‘œ μ „λ‹¬ν•˜λ©΄
더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŒ numpy의 ν–₯ν›„ λ²„μ „μ—μ„œλŠ” (μœ ν˜•,
(1,)) / '(1,)μœ ν˜•'. _np_qint32 = np.dtype([("qint32", np.int32, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\frameworkdtypes.py:525:
FutureWarning: (type, 1) λ˜λŠ” '1type'을 type의 λ™μ˜μ–΄λ‘œ μ „λ‹¬ν•˜λ©΄
더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŒ numpy의 ν–₯ν›„ λ²„μ „μ—μ„œλŠ” (μœ ν˜•,
(1,)) / '(1,)μœ ν˜•'. np_resource = np.dtype([("λ¦¬μ†ŒμŠ€", np.ubyte, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorboard\compat\tensorflow_stubdtypes.py:541:
FutureWarning: (type, 1) λ˜λŠ” '1type'을 type의 λ™μ˜μ–΄λ‘œ μ „λ‹¬ν•˜λ©΄
더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŒ numpy의 ν–₯ν›„ λ²„μ „μ—μ„œλŠ” (μœ ν˜•,
(1,)) / '(1,)μœ ν˜•'. _np_qint8 = np.dtype([("qint8", np.int8, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorboard\compat\tensorflow_stubdtypes.py:542:
FutureWarning: (type, 1) λ˜λŠ” '1type'을 type의 λ™μ˜μ–΄λ‘œ μ „λ‹¬ν•˜λ©΄
더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŒ numpy의 ν–₯ν›„ λ²„μ „μ—μ„œλŠ” (μœ ν˜•,
(1,)) / '(1,)μœ ν˜•'. _np_quint8 = np.dtype([("quint8", np.uint8, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorboard\compat\tensorflow_stubdtypes.py:543:
FutureWarning: (type, 1) λ˜λŠ” '1type'을 type의 λ™μ˜μ–΄λ‘œ μ „λ‹¬ν•˜λ©΄
더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŒ numpy의 ν–₯ν›„ λ²„μ „μ—μ„œλŠ” (μœ ν˜•,
(1,)) / '(1,)μœ ν˜•'. _np_qint16 = np.dtype([("qint16", np.int16, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorboard\compat\tensorflow_stubdtypes.py:544:
FutureWarning: (type, 1) λ˜λŠ” '1type'을 type의 λ™μ˜μ–΄λ‘œ μ „λ‹¬ν•˜λ©΄
더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŒ numpy의 ν–₯ν›„ λ²„μ „μ—μ„œλŠ” (μœ ν˜•,
(1,)) / '(1,)μœ ν˜•'. _np_quint16 = np.dtype([("quint16", np.uint16, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorboard\compat\tensorflow_stubdtypes.py:545:
FutureWarning: (type, 1) λ˜λŠ” '1type'을 type의 λ™μ˜μ–΄λ‘œ μ „λ‹¬ν•˜λ©΄
더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŒ numpy의 ν–₯ν›„ λ²„μ „μ—μ„œλŠ” (μœ ν˜•,
(1,)) / '(1,)μœ ν˜•'. _np_qint32 = np.dtype([("qint32", np.int32, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorboard\compat\tensorflow_stubdtypes.py:550:
FutureWarning: (type, 1) λ˜λŠ” '1type'을 type의 λ™μ˜μ–΄λ‘œ μ „λ‹¬ν•˜λ©΄
더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŒ numpy의 ν–₯ν›„ λ²„μ „μ—μ„œλŠ” (μœ ν˜•,
(1,)) / '(1,)μœ ν˜•'. np_resource = np.dtype([("λ¦¬μ†ŒμŠ€", np.ubyte, 1)])
κ²½κ³ : ν”Œλž˜κ·Έ ꡬ문 뢄석 전에 λ‘œκΉ…μ€ stderr둜 μ΄λ™ν•©λ‹ˆλ‹€. W1124 18:22:27.201594
10144 deprecation_wrapper.py:119] λ°œμ‹ μž
C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py:15:
tf.train.RMSPropOptimizerλΌλŠ” 이름은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. μ‚¬μš©ν•˜μ‹­μ‹œμ˜€
λŒ€μ‹  tf.compat.v1.train.RMSPropOptimizer. W1124 18:22:27.209591 10144
deprecation_wrapper.py:119] λ°œμ‹ μž
C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py:16:
tf.train.AdadeltaOptimizerλΌλŠ” 이름은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. μ‚¬μš©ν•˜μ‹­μ‹œμ˜€
λŒ€μ‹  tf.compat.v1.train.AdadeltaOptimizer. W1124 18:22:27.209591 10144
deprecation_wrapper.py:119] λ°œμ‹ μž
C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py:17:
tf.train.AdagradOptimizerλΌλŠ” 이름은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. μ‚¬μš©ν•˜μ‹­μ‹œμ˜€
λŒ€μ‹  tf.compat.v1.train.AdagradOptimizer. W1124 18:22:27.213590 10144
deprecation_wrapper.py:119] λ°œμ‹ μž
C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py:18:
tf.train.AdagradDAOptimizerλΌλŠ” 이름은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. μ‚¬μš©ν•˜μ‹­μ‹œμ˜€
λŒ€μ‹  tf.compat.v1.train.AdagradDAOptimizer. W1124 18:22:27.213590 10144
deprecation_wrapper.py:119] λ°œμ‹ μž
C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py:19:
tf.train.MomentumOptimizerλΌλŠ” 이름은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. μ‚¬μš©ν•˜μ‹­μ‹œμ˜€
λŒ€μ‹  tf.compat.v1.train.MomentumOptimizer. νŒŒμ‹±
./cfg/tiny-yolo-voc.cfg νŒŒμ‹± cfg/tiny-yolo-voc-1c.cfg λ‘œλ”©
bin/tiny-yolo-voc.weights ... μ„±κ³΅μ μœΌλ‘œ μ‹λ³„λœ 63471556λ°”μ΄νŠΈ
Finished in 0.019990205764770508s λΉŒλ”©λ„· ... W1124 18:22:27.253580
10144 deprecation_wrapper.py:119] λ°œμ‹ μž
C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py:105:
tf.placeholderλΌλŠ” 이름은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. tf.compat.v1.placeholderλ₯Ό μ‚¬μš©ν•˜μ„Έμš”.
λŒ€μ‹ μ—. 좜처 | κΈ°μ°¨? | λ ˆμ΄μ–΄ μ„€λͺ… | 좜λ ₯ 크기
-------+--------+--------------------------------- ------------------- W1124
18:22:27.257580 10144 deprecation_wrapper.py:119] λ°œμ‹ μž
C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\ops\baseop.py:70:
tf.variable_scopeλΌλŠ” 이름은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. μ‚¬μš©ν•˜μ‹­μ‹œμ˜€
λŒ€μ‹  tf.compat.v1.variable_scope. W1124 18:22:27.261598 10144
deprecation_wrapper.py:119] λ°œμ‹ μž
C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\ops\baseop.py:71:
tf.get_variableμ΄λΌλŠ” 이름은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. μ‚¬μš©ν•˜μ‹­μ‹œμ˜€
λŒ€μ‹  tf.compat.v1.get_variable. W1124 18:22:27.277594 10144
deprecation_wrapper.py:119] λ°œμ‹ μž
C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\ops\baseop.py:84:
tf.placeholder_with_defaultλΌλŠ” 이름은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. μ‚¬μš©ν•˜μ‹­μ‹œμ˜€
λŒ€μ‹  tf.compat.v1.placeholder_with_default. | | μž…λ ₯ | (?, 416, 416, 3)
λ‘œλ“œ | λ„€! | conv 3x3p1_1 +bnorm λˆ„μˆ˜ | (?, 416, 416, 16) W1124
18:22:27.389549 10144 deprecation_wrapper.py:119] λ°œμ‹ μž
C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\ops\simple.py:106:
tf.nn.max_poolμ΄λΌλŠ” 이름은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. λŒ€μ‹  tf.nn.max_pool2dλ₯Ό μ‚¬μš©ν•˜μ‹­μ‹œμ˜€.
λ‘œλ“œ | λ„€! | μ΅œλŒ€ 2x2p0_2 | (?, 208, 208, 16) λ‘œλ“œ | λ„€! | μ „ν™˜ 3x3p1_1
+bnorm μƒˆλŠ” | (?, 208, 208, 32) λ‘œλ“œ | λ„€! | μ΅œλŒ€ 2x2p0_2 | (?, 104, 104,
32) λ‘œλ“œ | λ„€! | conv 3x3p1_1 +bnorm λˆ„μˆ˜ | (?, 104, 104, 64) λ‘œλ“œ | λ„€!
| μ΅œλŒ€ 2x2p0_2 | (?, 52, 52, 64) λ‘œλ“œ | λ„€! | conv 3x3p1_1 +bnorm λˆ„μˆ˜ |
(?, 52, 52, 128) λ‘œλ“œ | λ„€! | μ΅œλŒ€ 2x2p0_2 | (?, 26, 26, 128) λ‘œλ“œ | λ„€!
| conv 3x3p1_1 +bnorm λˆ„μˆ˜ | (?, 26, 26, 256) λ‘œλ“œ | λ„€! | μ΅œλŒ€ 2x2p0_2 |
(?, 13, 13, 256) λ‘œλ“œ | λ„€! | conv 3x3p1_1 +bnorm λˆ„μˆ˜ | (?, 13, 13, 512)
λ‘œλ“œ | λ„€! | μ΅œλŒ€ 2x2p0_1 | (?, 13, 13, 512) λ‘œλ“œ | λ„€! | μ „ν™˜ 3x3p1_1
+bnorm μƒˆλŠ” | (?, 13, 13, 1024) λ‘œλ“œ | λ„€! | conv 3x3p1_1 +bnorm λˆ„μˆ˜ |
(?, 13, 13, 1024) μ΄ˆκΈ°ν™” | λ„€! | λ³€ν™˜ 1x1p0_1 μ„ ν˜• | (?, 13, 13, 30)
-------+--------+--------------------------------- ------------------- μ‹€ν–‰ 쀑
μ „μ μœΌλ‘œ CPU에 cfg/tiny-yolo-voc-1c.cfg 손싀 ν•˜μ΄νΌ λ§€κ°œλ³€μˆ˜: H = 13 W =
13 μƒμž = 5 클래슀 = 1 μ €μšΈ = [1.0, 5.0, 1.0, 1.0] W1124 18:22:29.962576
10144 deprecation.py:323] λ°œμ‹ μž
C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\yolov2\train.py:87:
to_float(tensorflow.python.ops.math_opsμ—μ„œ)λŠ” 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμœΌλ©° μ•žμœΌλ‘œλ„
ν–₯ν›„ λ²„μ „μ—μ„œ μ œκ±°λ©λ‹ˆλ‹€. μ—…λ°μ΄νŠΈ 지침: tf.cast μ‚¬μš©
λŒ€μ‹ μ—. λΉŒλ”© cfg/tiny-yolo-voc-1c.cfg loss W1124 18:22:30.010835 10144
deprecation_wrapper.py:119] λ°œμ‹ μž
C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\yolov2\train.py:107:
tf.summary.scalarλΌλŠ” 이름은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. μ‚¬μš©ν•˜μ‹­μ‹œμ˜€
λŒ€μ‹  tf.compat.v1.summary.scalar. cfg/tiny-yolo-voc-1c.cfg ꡬ좕
κΈ°μ°¨ op W1124 18:22:30.102793 10144 deprecation.py:323] From
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\ops\math_grad.py:1205:
add_dispatch_support..wrapper(tensorflow.python.ops.array_opsμ—μ„œ)λŠ”
더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμœΌλ©° ν–₯ν›„ λ²„μ „μ—μ„œ μ œκ±°λ©λ‹ˆλ‹€. 지침
μ—…λ°μ΄νŠΈ: λΈŒλ‘œλ“œμΊμŠ€νŠΈ κ·œμΉ™μ΄ λ™μΌν•œ 2.0μ—μ„œ tf.whereλ₯Ό μ‚¬μš©ν•©λ‹ˆλ‹€.
np.where W1124 18:22:32.038406 10144 deprecation.py:506] From
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\training\rmsprop.py:119:
원을 ν˜ΈμΆœν•©λ‹ˆλ‹€. dtype이 μžˆλŠ” init (tensorflow.python.ops.init_opsμ—μ„œ)λŠ” λ‹€μŒκ³Ό κ°™μŠ΅λ‹ˆλ‹€.
더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμœΌλ©° ν–₯ν›„ λ²„μ „μ—μ„œ μ œκ±°λ©λ‹ˆλ‹€. 지침
μ—…λ°μ΄νŠΈ: λŒ€μ‹  dtype 인수λ₯Ό μ‚¬μš©ν•˜μ—¬ μ΄ˆκΈ°ν™” μΈμŠ€ν„΄μŠ€λ₯Ό ν˜ΈμΆœν•©λ‹ˆλ‹€.
μƒμ„±μžμ— 전달 W1124 18:22:32.795700 10144
deprecation_wrapper.py:119] λ°œμ‹ μž
C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py:145:
tf.Sessionμ΄λΌλŠ” 이름은 더 이상 μ‚¬μš©λ˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€. λŒ€μ‹  tf.compat.v1.Session을 μ‚¬μš©ν•˜μ‹­μ‹œμ˜€.
2019-11-24 18:22:32.800843: λ‚˜
tensorflow/core/platform/cpu_feature_guard.cc:142] CPU 지원
이 TensorFlow λ°”μ΄λ„ˆλ¦¬κ°€ μ‚¬μš©ν•˜λ„λ‘ μ»΄νŒŒμΌλ˜μ§€ μ•Šμ€ λͺ…λ Ή: AVX2
11.774582862854004sμ—μ„œ μ™„λ£Œ ꡐ윑 μ‹œμž‘ ... cfg/tiny-yolo-voc-1c.cfg
ꡬ문 뢄석 annotations_clean ['vodafone']에 λŒ€ν•œ ꡬ문 뢄석
[=====================>]100% Image9.xml 톡계: 데이터 μ„ΈνŠΈ 크기: 53 데이터 μ„ΈνŠΈ
53개 μΈμŠ€ν„΄μŠ€ 쀑 Image20.jpg 역좔적(κ°€μž₯ 졜근 호좜 λ§ˆμ§€λ§‰): 파일
"flow", 6ν–‰, cliHandler(sys.argv) 파일
"C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\cli.py", 33ν–‰,
in cliHandler print('ν›ˆλ ¨ μž…λ ₯ ...'); tfnet.train() 파일
"C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\flow.py",
39ν–‰, in train for i, (x_batch, datum) in enumerate(batch): 파일
"C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\yolodata.py",
114ν–‰, μ…”ν”Œ inpμ—μ„œ new_feed = self._batch(train_instance) 파일
"C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\yolov2data.py",
28ν–‰, _batch img = self.preprocess(경둜, allobj) 파일
"C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\yolo\predict.py",
62ν–‰, μ „μ²˜λ¦¬ κ²°κ³Ό = imcv2_affine_trans(im) 파일
"C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflowutils\im_transform.py",
20ν–‰, imcv2_affine_trans h, w, c = im.shape AttributeError:
'NoneType' κ°μ²΄μ—λŠ” 'shape' 속성이 μ—†μŠ΅λ‹ˆλ‹€.
당신은 λŒ“κΈ€μ„ λ‹¬μ•˜μŠ΅λ‹ˆλ‹€. 이 이메일에 직접 λ‹΅μž₯ν•˜κ³  GitHub <#265μ—μ„œ ν™•μΈν•˜μ„Έμš”.
https://github.com/thtrieu/darkflow/issues/265 ?email_source=notifications&email_token=AGG23MNSSXWIHQFI75KYEWDQVJ3ORA5CNFSM4DNJVSV2YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63
λ˜λŠ” ꡬ독 μ·¨μ†Œ
https://github.com/notifications/unsubscribe-auth/AGG23MMETFBN5NG76IHGWZ3QVJ3ORANCNFSM4DNJVSVQ
.

μ•„λ‹ˆμš”, Image1, Image2, Image3... λ“± ν˜•μ‹μ˜ λͺ¨λ“  이미지λ₯Ό λ‹€μ‹œ μ‚¬μš©ν–ˆμŠ΅λ‹ˆλ‹€.
λͺ¨λ“  μ΄λ―Έμ§€μ—λŠ” .jpg ν˜•μ‹μ΄ μžˆμŠ΅λ‹ˆλ‹€.

β€”
당신이 λŒ“κΈ€μ„ λ‹¬μ•˜κΈ° λ•Œλ¬Έμ— 이것을 λ°›λŠ” κ²ƒμž…λ‹ˆλ‹€.
이 이메일에 직접 λ‹΅μž₯ν•˜κ³  GitHubμ—μ„œ ν™•μΈν•˜μ„Έμš”.
https://github.com/thtrieu/darkflow/issues/265?email_source=notifications&email_token=AGG23MJ2SKBIF2FQTPTLBRLQVJ4SVA5CNFSM4DNJVSV2YY3PNVWWK3TUL52HS4DFVEXG43VMVBW63
λ˜λŠ” ꡬ독 μ·¨μ†Œ
https://github.com/notifications/unsubscribe-auth/AGG23ML6HYW6S7JZEN2ZAF3QVJ4SVANCNFSM4DNJVSVQ
.

μ΄λ²ˆμ—λŠ” labelImgλ₯Ό μ‚¬μš©ν•˜μ—¬ 이미지에 λ‹€μ‹œ 주석을 λ‹¬μ•˜μ§€λ§Œ λ¬Έμ œλŠ” μ—¬μ „νžˆ μ§€μ†λ©λ‹ˆλ‹€.

Enter training ...

cfg/tiny-yolo-voc-1c.cfg parsing annotations_clean
Parsing for ['vodafone']
[====================>]100%  Image8.xml
Statistics:
vodafone: 59
Dataset size: 51
Dataset of 51 instance(s)
**Image7.jpg**
Traceback (most recent call last):
  File "flow", line 6, in <module>
    cliHandler(sys.argv)
  File "C:\Users\karanbari\Desktop\YOLO\darkflow-master\darkflow\cli.py", line 33, in cliHandler
    print('Enter training ...'); tfnet.train()
  File "C:\Users\karanbari\Desktop\YOLO\darkflow-master\darkflow\net\flow.py", line 39, in train
    for i, (x_batch, datum) in enumerate(batches):
  File "C:\Users\karanbari\Desktop\YOLO\darkflow-master\darkflow\net\yolo\data.py", line 114, in shuffle
    inp, new_feed = self._batch(train_instance)
  File "C:\Users\karanbari\Desktop\YOLO\darkflow-master\darkflow\net\yolov2\data.py", line 28, in _batch
    img = self.preprocess(path, allobj)
  File "C:\Users\karanbari\Desktop\YOLO\darkflow-master\darkflow\net\yolo\predict.py", line 62, in preprocess
    result = imcv2_affine_trans(im)
  File "C:\Users\karanbari\Desktop\YOLO\darkflow-master\darkflow\utils\im_transform.py", line 20, in imcv2_affine_trans
    h, w, c = im.shape
AttributeError: 'NoneType' object has no attribute 'shape'

여기에 λ‹€μ‹œ 였λ₯˜κ°€ 있고 Image7.jpg에 λŒ€ν•œ ν•΄λ‹Ή .xml 파일이 μžˆμŠ΅λ‹ˆλ‹€.

<annotation>
    <folder>train_clean</folder>
    <filename>Image7.jpg</filename>
    <path>C:\Users\karanbari\Desktop\YOLO\images\train_clean\Image7.jpg</path>
    <source>
        <database>Unknown</database>
    </source>
    <size>
        <width>1300</width>
        <height>1390</height>
        <depth>3</depth>
    </size>
    <segmented>0</segmented>
    <object>
        <name>vodafone</name>
        <pose>Unspecified</pose>
        <truncated>0</truncated>
        <difficult>0</difficult>
        <bndbox>
            <xmin>370</xmin>
            <ymin>258</ymin>
            <xmax>916</xmax>
            <ymax>792</ymax>
        </bndbox>
    </object>
</annotation>

λ„£μ–΄μ£ΌλŠ”κ²Œ λ‚«λ‹€
print(im, type(im))
L58의 darkflow/net/yolo/predict.pyμ—μ„œ 직접 경둜λ₯Ό ν™•μΈν•˜μ‹­μ‹œμ˜€.

같은 였λ₯˜κ°€ λ°œμƒν–ˆμŠ΅λ‹ˆλ‹€

λ‚˜λŠ” 같은 λ¬Έμ œμ— μ§λ©΄ν–ˆκ³  λ‚΄ μˆ˜μ • 사항은 λ‹€μŒκ³Ό κ°™μŠ΅λ‹ˆλ‹€.
predict.py 라인# 60μ—μ„œ im = cv2.imread(im) 을 im = cv2.imread(im+'.jpg') 둜 λ³€κ²½ν–ˆμŠ΅λ‹ˆλ‹€.

λ‚˜λŠ” 같은 λ¬Έμ œκ°€ μžˆμ—ˆκ³  jpg 이미지λ₯Ό μ‚­μ œν–ˆμ§€λ§Œ 주석을 μ‚­μ œν•˜λŠ” 것을 μžŠμ—ˆκΈ° λ•Œλ¬Έμž…λ‹ˆλ‹€. λ”°λΌμ„œ 이미지와 주석이 일관성이 μžˆλŠ”μ§€ ν™•μΈν•˜μ‹­μ‹œμ˜€.

이 νŽ˜μ΄μ§€κ°€ 도움이 λ˜μ—ˆλ‚˜μš”?
0 / 5 - 0 λ“±κΈ‰