μλ ,
λλ μλ‘μ΄ λ°μ΄ν° μΈνΈλ₯Ό νλ ¨νκ³ μμ΅λλ€. κ·Έλ¬λ νλ ¨μ νμ λͺ λ¨κ³ λμ μ€νλλ©° κ°μκΈ° λ€μ μ€λ₯κ° λ°μν©λλ€. "AttributeError: 'NoneType' object has no attribute 'shape'". κ΅μ‘μ΄ λͺ λ¨κ³ λμ μ€νλ μ μκ³ μΆκ° λ¬Έμ ν΄κ²° λ°©λ²μ λν μμ΄λμ΄κ° μ€νλκ³ μμΌλ―λ‘ μ£Όμ νμΌμ μ£Όμ νμκ³Ό νμΌ μ΄λ¦μ΄ μ ννλ€κ³ μκ°ν©λλ€.
μ΄μ λν μμ΄λμ΄λ λμμ κ°μ¬λ립λλ€.
κ°μ¬ν©λλ€.
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'
xml νμΌμ νμΈνμμμ€. νμΌ μ΄λ¦μ μ΄λ―Έμ§ νμ₯μκ° ν¬ν¨λμ΄ μμ΅λκΉ?
μ, νμΌ μ΄λ¦μλ λ΄ μ΄λ―Έμ§μ νμ₯μκ° .jpgλ‘ ν¬ν¨λμ΄ μμ΅λλ€.
λ€μμ xml νμΌ μ€ νλμ λλ€.
<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 κ·Έκ²μ΄ μλνμ§ μλ κ²μ 보면 - κ²½λ‘ μμ΄ νμΌ μ΄λ¦μ λ£μ΄λ³΄κ³ (μ: <filename>000004.jpg</filename>
) νλ ¨μ μλν λ λ³κ²½λλ μ¬νμ΄ μλμ§ νμΈν μ μμ΅λκΉ?
@abagshaw μ μ κ°μ¬ν©λλ€. κ²½λ‘ μμ΄ νμΌ μ΄λ¦μ λ£μΌλ €κ³ νμ§λ§ μ¬μ ν λμΌν μ€λ₯κ° λ°μν©λλ€.
λ€λ₯Έ μμ΄λμ΄κ° μμ΅λκΉ?
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΄μν μ μ 첫 λ²μ§Έ λ¨κ³μμ μ€λ₯κ° λ°μνμ§ μλλ€λ κ²μ
λλ€...μ΄λ .xml
νμΌ μ€ μΌλΆλ μ λλ‘ κ΅¬μ±λκ³ λλ¨Έμ§λ κ·Έλ μ§ μλ€λ κ²μ λνλΌ μ μμ΅λλ€. νμΌμ _λͺ¨λ _μ΄ <filename>000004.jpg</filename>
νμμ μ¬μ©νλ€κ³ 100% νμ νμλκΉ? νλ(λλ κ·Έ μ΄μ)κ° μ λλ‘ κ΅¬μ±λμ§ μμμ κ°λ₯μ±μ΄ μμ΅λκΉ? μ΄ λͺ¨λ νμΌμ νμμ μ΄λ»κ² μμ νκ³ μλμ§ μ λͺ¨λ₯΄κ² μ΅λλ€... νμ§λ§ λꡬλ₯Ό μ¬μ©νμ¬ λ§μ νμΌμ μΌκ΄ μμ νλ κ²½μ° μΌλΆκ° λλ½λ μ μμ΅λκΉ?
λ΄κ° μκ°ν μμλ μ μΌν λ€λ₯Έ κ²μ μΌλΆ μ΄λ―Έμ§κ° /ml/data/new/JPEGImages
μμ μ κ±°λμμ§λ§ ν΄λΉ .xml
νμΌμ΄ /ml/data/new/Annotations
μμ μ κ±°λμ§ μμλ€λ κ²μ
λλ€. /ml/data/new/JPEGImages
μ μλ μ΄λ―Έμ§μ κ°μ μμ .xml
νμΌμ΄ /ml/data/new/Annotations
$ μ μμ΅λκΉ?
λλ κ³Όκ±°μ μ΄κ²μ λ§λ¬λ€. μΌλΆ .xml
λλ .jpg
νμΌμ΄ μ λλ‘ λͺ
λͺ
/ꡬμ±λμ§ μμμ κ°λ₯μ±μ΄ λμ΅λλ€. 무μμ΄ μλͺ»λμλμ§ λλ²κΉ
νλ ν κ°μ§ λ°©λ²μ λ€μμ μΆκ°νλ κ²μ
λλ€.
print(jpg)
μ΄ μ€ μ΄ν: https://github.com/thtrieu/darkflow/blob/master/darkflow/net/yolov2/data.py#L26
λ°λΌμ μμλ νμΌμ μ΄λ¦μ λ³΄κ³ .xml
λλ .jpg
μ€ νλλ₯Ό μ‘°μ¬ν μ μμ΅λλ€.
@abagshaw μ @thtrieuμκ² κ°μ¬λ립λλ€! λλΉ, λμ΄, ymin, ymax, xmin λ° xmax κ°μ νμΈνκΈ° μν΄ xml νμΌμ ꡬ문 λΆμνλ Python μ€ν¬λ¦½νΈλ₯Ό μμ±νμ¬ λ¬Έμ μ μμΈμ μ°Ύμμ΅λλ€. λ¬Έμ λ opencvμμ μ λλ‘ λ‘λν μ μλ λ κ°μ jpg νμΌλ‘ μΈν΄ λ°μνλ―λ‘ labelImgμμ μμ±ν xml νμΌμμ λλΉμ λμ΄κ° 0μΌλ‘ μ§μ λ©λλ€.
@thtrieu μ μ μμ λ§μ λμμ΄ λ©λλ€. λ¬Έμ .jpg λλ .xmlμ μ°ΎκΈ° μν΄ μΈμλ₯Ό μ¬μ©νμ§ μμμ΅λλ€.
darkflowλ₯Ό μμνλ μ¬λμ΄λΌλ©΄ λꡬλ μμ μ νκ²½μμ μλνλμ§ νμΈνκ³ μΆμ λΏμ
λλ€. λ΄κ° μκ°ν΄ λΈ λ¬Έμ λ‘ μΈν΄ μ¬κΈ°μμ μμ κ²°λ‘ μ λ΄λ Έμ΅λλ€.
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 μ€ν¬λ¦½νΈλ₯Ό 곡μ ν΄ μ£Όμ€ μ μμ΅λκΉ?
λλ κ³Όκ±°μ μ΄κ²μ λ§λ¬λ€. μΌλΆ
.xml
λλ.jpg
νμΌμ΄ μ λλ‘ λͺ λͺ /ꡬμ±λμ§ μμμ κ°λ₯μ±μ΄ λμ΅λλ€. 무μμ΄ μλͺ»λμλμ§ λλ²κΉ νλ ν κ°μ§ λ°©λ²μ λ€μμ μΆκ°νλ κ²μ λλ€.print(jpg)
μ΄ μ€ μ΄ν: https://github.com/thtrieu/darkflow/blob/master/darkflow/net/yolov2/data.py#L26
λ°λΌμ μμλ νμΌμ μ΄λ¦μ 보κ³
.xml
λλ.jpg
μ€ νλλ₯Ό μ‘°μ¬ν μ μμ΅λλ€.
jpegμΈ κ²½μ° λ¬Έμ λ₯Ό ν΄κ²°νλ €λ©΄ μ΄λ»κ² ν΄μΌ ν©λκΉ? λλ κ°μ λ¬Έμ κ° μμκ³ μΈμ λ¬Έμ μ€ννμ΅λλ€.
λλμ΄ μΆλ ₯μ μ»μλ€ :
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**
λ λ²μ§Έ μ΄λ―Έμ§ νμΌ λ€μ .jpgκ° μλ€λ μ μΈμλ κ·Έκ² μ νν 무μμ μλ―Ένλμ§ λͺ¨λ₯΄κ² μ΅λλ€.
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'
μ΄ μ€λ₯κ° λ°μνλ©΄ ν΄κ²° λ°©λ² plz help
@wendq86 κ·Έκ²μ΄ μλνμ§ μλ κ²μ 보면 - κ²½λ‘ μμ΄ νμΌ μ΄λ¦μ λ£μ΄λ³΄κ³ (μ:
<filename>000004.jpg</filename>
) νλ ¨μ μλν λ λ³κ²½λλ μ¬νμ΄ μλμ§ νμΈν μ μμ΅λκΉ?
μ΄κ²μ λλ₯Ό μν΄ μΌνμ΅λλ€
μλ νμΈμ, COCO λ°μ΄ν° μΈνΈλ₯Ό νλ ¨νλ €κ³ ν λ λμΌν λ¬Έμ μ μ§λ©΄νμ΅λλ€. μ΄ λ¬Έμ λ₯Ό ν΄κ²°νλ λ°©λ²μ λ€μκ³Ό κ°μ΅λλ€.
https://github.com/tylin/coco-dpm/blob/master/coco/convert_to_pascalformat.py λ₯Ό μ¬μ©νμ¬ COCO json νμμ XML νμμΌλ‘ λ³νν©λλ€.
κ·Έλ¬λ μ΄ μ XML νμΌμ νμμ΄ darkflowμ μμ (darkflow/test/training/annotations)μ μλ VOC XML νμκ³Ό λμΌνλλ‘ μ€ν¬λ¦½νΈμ μΌλΆλ₯Ό μμ ν΄μΌ ν©λλ€. μλ₯Ό λ€μ΄:
1λ¨κ³ μ€ν¬λ¦½νΈμ COCO XMLμ λ€μκ³Ό κ°μ΅λλ€.
<tag1>
xxxxx
</tag1>
<tag2>
xxxxx
</tag2>
κ·Έλ¬λ λ€μκ³Ό κ°μ νμμ΄ νμν©λλ€.
<tag1>xxxxx</tag>
<tag2>xxxxx</tag2>
3 'label.txt' νμΌμμ 'tvmonitor'λ₯Ό 'tv'λ‘ λ³κ²½
λλ λͺ¨λ jpeg μ΄λ―Έμ§λ₯Ό μμ νκ³ μλνμ΅λλ€
μλ ,
λλ μλ‘μ΄ λ°μ΄ν° μΈνΈλ₯Ό νλ ¨νκ³ μμ΅λλ€. κ·Έλ¬λ νλ ¨μ νμ λͺ λ¨κ³ λμ μ€νλλ©° κ°μκΈ° λ€μ μ€λ₯κ° λ°μν©λλ€. "AttributeError: 'NoneType' object has no attribute 'shape'". κ΅μ‘μ΄ λͺ λ¨κ³ λμ μ€νλ μ μκ³ μΆκ° λ¬Έμ ν΄κ²° λ°©λ²μ λν μμ΄λμ΄κ° μ€νλκ³ μμΌλ―λ‘ μ£Όμ νμΌμ μ£Όμ νμκ³Ό νμΌ μ΄λ¦μ΄ μ ννλ€κ³ μκ°ν©λλ€.
μ΄μ λν μμ΄λμ΄λ λμμ κ°μ¬λ립λλ€.
κ°μ¬ν©λλ€.
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 μ΄λ―Έμ§ μμ
μλ
νμΈμ, μ λ μ¬μ©μ μ μ κ°μ²΄ κ°μ§λ₯Ό νλ ¨νμ¬ νμ¬ λ‘κ³ λ₯Ό κ°μ§νλ €κ³ λ
Έλ ₯νκ³ μμ΅λλ€. μ΄ μ€λ₯κ° λ°μν λκΉμ§ λͺ¨λ κ²μ΄ μ μ§νλμμ΅λλ€. λν μ΄λ―Έμ§λ₯Ό λ€μ μμ νκ³ μ£Όμμ λ¬μμ§λ§ κ²°κ³Όμλ μλ¬΄λ° λ³νκ° μμμ΅λλ€. λκ΅°κ° μ΄κ²μ λμμ£ΌμΈμ.
κ°μ¬ ν΄μ
(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'
μ΄λ―Έμ§ μ΄λ¦μ νΉμ λ¬Έμκ° μμ΅λκΉ? κ·Έλ λ€λ©΄ λ³κ²½νμμμ€.
2019λ 11μ 24μΌ μΌμμΌ μ€ν 6μ 32λΆμ karan bari [email protected] μμ λ€μκ³Ό κ°μ΄ μΌμ΅λλ€.
μλ νμΈμ, μ λ μ¬μ©μ μ μ κ°μ²΄ κ°μ§λ₯Ό νλ ¨νμ¬ λ΄
νμ¬ λ‘κ³ ,μ΄ μ€λ₯κΉμ§ λͺ¨λ κ²μ΄ μλμμ΅λλ€. λλ μμ νκ³
μ΄λ―Έμ§μ λ€μ μ£Όμμ λ¬μμ§λ§ κ²°κ³Όμλ λ³νκ° μμμ΅λλ€. λκ΅°κ° λΆνν΄λ λ κΉμ?
λμμ€
κ°μ¬ ν΄μ(κΈ°λ³Έ) C:\Users\karanbari>cd Desktop/YOLO/darkflow-master
(κΈ°λ³Έ) C:\Users\karanbari\Desktop\YOLOdarkflow-master>python νλ¦ --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) λλ '1type'μ λμμ΄λ‘ μ λ¬νλ κ²μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. numpyμ ν₯ν λ²μ μμλ (type, (1,)) / '(1,)type'μΌλ‘ μ΄ν΄λ κ²μ λλ€.
_np_qint8 = np.dtype([("qint8", np.int8, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\frameworkdtypes.py:517: FutureWarning: (type, 1) λλ '1type'μ λμμ΄λ‘ μ λ¬νλ κ²μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. numpyμ ν₯ν λ²μ μμλ (type, (1,)) / '(1,)type'μΌλ‘ μ΄ν΄λ κ²μ λλ€.
_np_quint8 = np.dtype([("quint8", np.uint8, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\frameworkdtypes.py:518: FutureWarning: (type, 1) λλ '1type'μ λμμ΄λ‘ μ λ¬νλ κ²μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. numpyμ ν₯ν λ²μ μμλ (type, (1,)) / '(1,)type'μΌλ‘ μ΄ν΄λ κ²μ λλ€.
_np_qint16 = np.dtype([("qint16", np.int16, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\frameworkdtypes.py:519: FutureWarning: (type, 1) λλ '1type'μ λμμ΄λ‘ μ λ¬νλ κ²μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. numpyμ ν₯ν λ²μ μμλ (type, (1,)) / '(1,)type'μΌλ‘ μ΄ν΄λ κ²μ λλ€.
_np_quint16 = np.dtype([("quint16", np.uint16, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\frameworkdtypes.py:520: FutureWarning: (type, 1) λλ '1type'μ λμμ΄λ‘ μ λ¬νλ κ²μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. numpyμ ν₯ν λ²μ μμλ (type, (1,)) / '(1,)type'μΌλ‘ μ΄ν΄λ κ²μ λλ€.
_np_qint32 = np.dtype([("qint32", np.int32, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\frameworkdtypes.py:525: FutureWarning: (type, 1) λλ '1type'μ λμμ΄λ‘ μ λ¬νλ κ²μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. numpyμ ν₯ν λ²μ μμλ (type, (1,)) / '(1,)type'μΌλ‘ μ΄ν΄λ κ²μ λλ€.
np_resource = np.dtype([("리μμ€", np.ubyte, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorboard\compat\tensorflow_stubdtypes.py:541: FutureWarning: (type, 1) λλ '1type'μ λμμ΄λ‘ μ λ¬νλ κ²μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. numpyμ ν₯ν λ²μ μμλ (type, (1,)) / '(1,)type'μΌλ‘ μ΄ν΄λ κ²μ λλ€.
_np_qint8 = np.dtype([("qint8", np.int8, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorboard\compat\tensorflow_stubdtypes.py:542: FutureWarning: (type, 1) λλ '1type'μ λμμ΄λ‘ μ λ¬νλ κ²μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. numpyμ ν₯ν λ²μ μμλ (type, (1,)) / '(1,)type'μΌλ‘ μ΄ν΄λ κ²μ λλ€.
_np_quint8 = np.dtype([("quint8", np.uint8, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorboard\compat\tensorflow_stubdtypes.py:543: FutureWarning: (type, 1) λλ '1type'μ λμμ΄λ‘ μ λ¬νλ κ²μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. numpyμ ν₯ν λ²μ μμλ (type, (1,)) / '(1,)type'μΌλ‘ μ΄ν΄λ κ²μ λλ€.
_np_qint16 = np.dtype([("qint16", np.int16, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorboard\compat\tensorflow_stubdtypes.py:544: FutureWarning: (type, 1) λλ '1type'μ λμμ΄λ‘ μ λ¬νλ κ²μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. numpyμ ν₯ν λ²μ μμλ (type, (1,)) / '(1,)type'μΌλ‘ μ΄ν΄λ κ²μ λλ€.
_np_quint16 = np.dtype([("quint16", np.uint16, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorboard\compat\tensorflow_stubdtypes.py:545: FutureWarning: (type, 1) λλ '1type'μ λμμ΄λ‘ μ λ¬νλ κ²μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. numpyμ ν₯ν λ²μ μμλ (type, (1,)) / '(1,)type'μΌλ‘ μ΄ν΄λ κ²μ λλ€.
_np_qint32 = np.dtype([("qint32", np.int32, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorboard\compat\tensorflow_stubdtypes.py:550: FutureWarning: (type, 1) λλ '1type'μ λμμ΄λ‘ μ λ¬νλ κ²μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. numpyμ ν₯ν λ²μ μμλ (type, (1,)) / '(1,)type'μΌλ‘ μ΄ν΄λ κ²μ λλ€.
np_resource = np.dtype([("리μμ€", np.ubyte, 1)])
κ²½κ³ : νλκ·Έ ꡬ문 λΆμ μ μ λ‘κΉ μ stderrλ‘ μ΄λν©λλ€.
W1124 18:22:27.201594 10144 deprecation_wrapper.py:119] C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py:15μμ: tf.train.RMSPropOptimizerλΌλ μ΄λ¦μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. λμ tf.compat.v1.train.RMSPropOptimizerλ₯Ό μ¬μ©νμμμ€.W1124 18:22:27.209591 10144 deprecation_wrapper.py:119] C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py:16μμ: tf.train.AdadeltaOptimizerλΌλ μ΄λ¦μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. λμ tf.compat.v1.train.AdadeltaOptimizerλ₯Ό μ¬μ©νμμμ€.
W1124 18:22:27.209591 10144 deprecation_wrapper.py:119] C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py:17μμ: tf.train.AdagradOptimizerλΌλ μ΄λ¦μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. λμ tf.compat.v1.train.AdagradOptimizerλ₯Ό μ¬μ©νμμμ€.
W1124 18:22:27.213590 10144 deprecation_wrapper.py:119] C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py:18μμ: tf.train.AdagradDAOptimizerλΌλ μ΄λ¦μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. λμ tf.compat.v1.train.AdagradDAOptimizerλ₯Ό μ¬μ©νμμμ€.
W1124 18:22:27.213590 10144 deprecation_wrapper.py:119] C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py:19μμ: tf.train.MomentumOptimizerλΌλ μ΄λ¦μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. λμ tf.compat.v1.train.MomentumOptimizerλ₯Ό μ¬μ©νμμμ€.
./cfg/tiny-yolo-voc.cfg ꡬ문 λΆμ
cfg/tiny-yolo-voc-1c.cfg ꡬ문 λΆμ
bin/tiny-yolo-voc.weights λ‘λ μ€ ...
63471556λ°μ΄νΈλ₯Ό μ±κ³΅μ μΌλ‘ μλ³νμ΅λλ€.
μλ£ 0.019990205764770508sκ΅¬μΆ κ·Έλ¬Ό ...
W1124 18:22:27.253580 10144 deprecation_wrapper.py:119] C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py:105μμ: tf.placeholderλΌλ μ΄λ¦μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. λμ tf.compat.v1.placeholderλ₯Ό μ¬μ©νμΈμ.μΆμ² | κΈ°μ°¨? | λ μ΄μ΄ μ€λͺ | μΆλ ₯ ν¬κΈ°
-------+--------+--------------------------------- -------------------
W1124 18:22:27.257580 10144 deprecation_wrapper.py:119] C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\ops\baseop.py:70μμ: tf.variable_scopeλΌλ μ΄λ¦μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. λμ tf.compat.v1.variable_scopeλ₯Ό μ¬μ©νμΈμ.W1124 18:22:27.261598 10144 deprecation_wrapper.py:119] C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\ops\baseop.py:71μμ: tf.get_variable μ΄λ¦μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. λμ tf.compat.v1.get_variableμ μ¬μ©νμμμ€.
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_defaultλΌλ μ΄λ¦μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. λμ tf.compat.v1.placeholder_with_defaultλ₯Ό μ¬μ©νμΈμ.
| | input | (?, 416, 416, 3)
λ‘λ | λ€! | conv 3x3p1_1 +bnorm λμ | (?, 416, 416, 16)
W1124 18:22:27.389549 10144 deprecation_wrapper.py:119] C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\ops\simple.py:106μμ: tf.nn.max_poolμ΄λΌλ μ΄λ¦μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. λμ tf.nn.max_pool2dλ₯Ό μ¬μ©νμμμ€.λ‘λ | λ€! | μ΅λ 2x2p0_2 | (?, 208, 208, 16)
λ‘λ | λ€! | conv 3x3p1_1 +bnorm λμ | (?, 208, 208, 32)
λ‘λ | λ€! | μ΅λ 2x2p0_2 | (?, 104, 104, 32)
λ‘λ | λ€! | conv 3x3p1_1 +bnorm λμ | (?, 104, 104, 64)
λ‘λ | λ€! | μ΅λ 2x2p0_2 | (?, 52, 52, 64)
λ‘λ | λ€! | conv 3x3p1_1 +bnorm λμ | (?, 52, 52, 128)
λ‘λ | λ€! | μ΅λ 2x2p0_2 | (?, 26, 26, 128)
λ‘λ | λ€! | conv 3x3p1_1 +bnorm λμ | (?, 26, 26, 256)
λ‘λ | λ€! | μ΅λ 2x2p0_2 | (?, 13, 13, 256)
λ‘λ | λ€! | conv 3x3p1_1 +bnorm λμ | (?, 13, 13, 512)
λ‘λ | λ€! | μ΅λ 2x2p0_1 | (?, 13, 13, 512)
λ‘λ | λ€! | conv 3x3p1_1 +bnorm λμ | (?, 13, 13, 1024)
λ‘λ | λ€! | conv 3x3p1_1 +bnorm λμ | (?, 13, 13, 1024)
μ΄κΈ°ν | λ€! | λ³ν 1x1p0_1 μ ν | (?, 13, 13, 30)
-------+--------+--------------------------------- -------------------
CPUμμ μμ ν μ€ν
cfg/tiny-yolo-voc-1c.cfg μμ€ νμ΄νΌ 맀κ°λ³μ:
H = 13
μΉ = 13
μμ = 5
ν΄λμ€ = 1
μ²λ = [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.opsedμμ) is deprethon.ma ν₯ν λ²μ μμ μ κ±°λ©λλ€.
μ λ°μ΄νΈ μ§μΉ¨:
λμtf.cast
λ₯Ό μ¬μ©νμμμ€.
cfg/tiny-yolo-voc-1c.cfg μμ€ κ΅¬μΆ
W1124 18:22:30.010835 10144 deprecation_wrapper.py:119] C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\yolov2\train.py:107μμ: tf.summary.scalarλΌλ μ΄λ¦μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. λμ tf.compat.v1.summary.scalarλ₯Ό μ¬μ©νμμμ€.건물 cfg/tiny-yolo-voc-1c.cfg κΈ°μ°¨ μμ
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_supportμμ..wrapper(tensorflow.python.ops.array_opsμμ)λ λ μ΄μ μ¬μ©λμ§ μμΌλ©° ν₯ν λ²μ μμ μ κ±°λ©λλ€.
μ λ°μ΄νΈ μ§μΉ¨:
np.whereμ λΈλ‘λμΊμ€νΈ κ·μΉμ΄ λμΌν 2.0μμ tf.whereλ₯Ό μ¬μ©ν©λλ€.
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__ νΈμΆ(ν μνλ‘μ°μμ .ops.init_ops) dtypeμ μ¬μ©νλ κ²μ λ μ΄μ μ¬μ©λμ§ μμΌλ©° ν₯ν λ²μ μμ μ κ±°λ©λλ€.
μ λ°μ΄νΈ μ§μΉ¨:
μμ±μμ μ λ¬νλ λμ dtype μΈμλ₯Ό μ¬μ©νμ¬ μ΄κΈ°ν μΈμ€ν΄μ€λ₯Ό νΈμΆν©λλ€.
W1124 18:22:32.795700 10144 deprecation_wrapper.py:119] C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py:145μμ: tf.Sessionμ΄λΌλ μ΄λ¦μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. λμ tf.compat.v1.Sessionμ μ¬μ©νμμμ€.2019-11-24 18:22:32.800843: I tensorflow/core/platform/cpu_feature_guard.cc:142] κ·νμ CPUλ μ΄ TensorFlow λ°μ΄λλ¦¬κ° μ¬μ©νλλ‘ μ»΄νμΌλμ§ μμ λͺ λ Ήμ μ§μν©λλ€: AVX2
11.774582862854004sμμ μλ£νλ ¨μ λ€μ΄κ°λ€ ...
cfg/tiny-yolo-voc-1c.cfg μ£Όμ ꡬ문 λΆμ
['보λ€ν°'] ꡬ문 λΆμ
[=====================>]100% Image9.xml
ν΅κ³:
λ°μ΄ν° μΈνΈ ν¬κΈ°: 53
53κ° μΈμ€ν΄μ€μ λ°μ΄ν°μΈνΈ
μ΄λ―Έμ§20.jpg
μμΆμ (κ°μ₯ μ΅κ·Ό νΈμΆ λ§μ§λ§):
νμΌ "νλ¦", 6ν,
cliHandler(sys.argv)
νμΌ "C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\cli.py", 33ν, cliHandler
print('νλ ¨ μ λ ₯...'); tfnet.train()
νμΌ "C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\flow.py", 39ν, κΈ°μ°¨
enumerate(batch)μ i, (x_batch, datum):
νμΌ "C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\yolodata.py", 114ν, μ ν
inp, new_feed = self._batch(train_instance)
νμΌ "C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\yolov2data.py", 28ν, _batch
img = self.preprocess(κ²½λ‘, allobj)
νμΌ "C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\yolo\predict.py", 62ν, μ μ²λ¦¬ μ€
κ²°κ³Ό = imcv2_affine_trans(im)
imcv2_affine_transμ νμΌ "C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflowutils\im_transform.py", 20ν
h, w, c = im.shape
AttributeError: 'NoneType' κ°μ²΄μ 'shape' μμ±μ΄ μμ΅λλ€.β
λΉμ μ΄ λκΈμ λ¬μκΈ° λλ¬Έμ μ΄κ²μ λ°λ κ²μ λλ€.
μ΄ μ΄λ©μΌμ μ§μ λ΅μ₯νκ³ GitHubμμ νμΈνμΈμ.
https://github.com/thtrieu/darkflow/issues/265?email_source=notifications&email_token=AGG23MNSSXWIHQFI75KYEWDQVJ3ORA5CNFSM4DNJVSV2YY3PNVWWK3TUL52HS4DFVEXG43VMVBW63LN
λλ ꡬλ μ·¨μ
https://github.com/notifications/unsubscribe-auth/AGG23MMETFBN5NG76IHGWZ3QVJ3ORANCNFSM4DNJVSVQ
.
μ΄λ―Έμ§ μ΄λ¦μ νΉμ λ¬Έμκ° μμ΅λκΉ? κ·Έλ λ€λ©΄ λ³κ²½νμμμ€.
β¦
2019λ 11μ 24μΌ μΌμμΌ μ€ν 6μ 32λΆ, karan bari @ . * > μμ±: μλ νμΈμ, μ λ νμ¬ λ‘κ³ λ₯Ό κ°μ§νκΈ° μν΄ μ¬μ©μ μ§μ κ°μ²΄ κ°μ§λ₯Ό νλ ¨νλ €κ³ ν©λλ€. μ΄ μ€λ₯κ° λ°μν λκΉμ§ λͺ¨λ κ²μ΄ μ μ§νλμμ΅λλ€. λν μ΄λ―Έμ§λ₯Ό λ€μ μμ νκ³ μ£Όμμ λ¬μμ§λ§ κ²°κ³Όμλ λ³νκ° μμμ΅λλ€. λκ΅°κ° μ΄ μμ μ λμμ€ μ μμ΅λκΉ? κ°μ¬ν©λλ€(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) λλ '1type'μ λμμ΄λ‘ μ λ¬νλ κ²μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. numpyμ ν₯ν λ²μ μμλ (type, (1,)) / '(1,)type'μΌλ‘ μ΄ν΄λ κ²μ λλ€. _np_qint8 = np.dtype([("qint8", np.int8, 1)]) C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\frameworkdtypes.py:517: FutureWarning: ν΅κ³Ό(μ ν , 1) μ νμ λμμ΄μΈ '1type'μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. numpyμ ν₯ν λ²μ μμλ (type, (1,)) / '(1,)type'μΌλ‘ μ΄ν΄λ κ²μ λλ€. _np_quint8 = np.dtype([("quint8", np.uint8, 1)]) C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\frameworkdtypes.py:518: FutureWarning: ν΅κ³Ό(μ ν , 1) μ νμ λμμ΄μΈ '1type'μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. numpyμ ν₯ν λ²μ μμλ (type, (1,)) / '(1,)type'μΌλ‘ μ΄ν΄λ κ²μ λλ€. _np_qint16 = np.dtype([("qint16", np.int16, 1)]) C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\frameworkdtypes.py:519: FutureWarning: ν΅κ³Ό(μ ν , 1) μ νμ λμμ΄μΈ '1type'μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. numpyμ ν₯ν λ²μ μμλ (type, (1,)) / '(1,)type'μΌλ‘ μ΄ν΄λ κ²μ λλ€. _np_quint16 = np.dtype([("quint16", np.uint16, 1)]) C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\frameworkdtypes.py:520: FutureWarning: ν΅κ³Ό(μ ν , 1) μ νμ λμμ΄μΈ '1type'μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. numpyμ ν₯ν λ²μ μμλ (type, (1,)) / '(1,)type'μΌλ‘ μ΄ν΄λ κ²μ λλ€. _np_qint32 = np.dtype([("qint32", np.int32, 1)]) C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\frameworkdtypes.py:525: FutureWarning: ν΅κ³Ό(μ ν , 1) μ νμ λμμ΄μΈ '1type'μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. numpyμ ν₯ν λ²μ μμλ (type, (1,)) / '(1,)type'μΌλ‘ μ΄ν΄λ κ²μ λλ€. np_resource = np.dtype([("resource", np.ubyte, 1)]) C:\Users\karanbari\Anaconda3\lib\site-packages\tensorboard\compat\tensorflow_stubdtypes.py:541: FutureWarning: ν΅κ³Ό(μ ν , 1) μ νμ λμμ΄μΈ '1type'μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. numpyμ ν₯ν λ²μ μμλ (type, (1,)) / '(1,)type'μΌλ‘ μ΄ν΄λ κ²μ λλ€. _np_qint8 = np.dtype([("qint8", np.int8, 1)]) C:\Users\karanbari\Anaconda3\lib\site-packages\tensorboard\compat\tensorflow_stubdtypes.py:542: FutureWarning: ν΅κ³Ό(μ ν , 1) μ νμ λμμ΄μΈ '1type'μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. numpyμ ν₯ν λ²μ μμλ (type, (1,)) / '(1,)type'μΌλ‘ μ΄ν΄λ κ²μ λλ€. _np_quint8 = np.dtype([("quint8", np.uint8, 1)]) C:\Users\karanbari\Anaconda3\lib\site-packages\tensorboard\compat\tensorflow_stubdtypes.py:543: FutureWarning: ν΅κ³Ό(μ ν , 1) μ νμ λμμ΄μΈ '1type'μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. numpyμ ν₯ν λ²μ μμλ (type, (1,)) / '(1,)type'μΌλ‘ μ΄ν΄λ κ²μ λλ€. _np_qint16 = np.dtype([("qint16", np.int16, 1)]) C:\Users\karanbari\Anaconda3\lib\site-packages\tensorboard\compat\tensorflow_stubdtypes.py:544: FutureWarning: ν΅κ³Ό(μ ν , 1) μ νμ λμμ΄μΈ '1type'μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. numpyμ ν₯ν λ²μ μμλ (type, (1,)) / '(1,)type'μΌλ‘ μ΄ν΄λ κ²μ λλ€. _np_quint16 = np.dtype([("quint16", np.uint16, 1)]) C:\Users\karanbari\Anaconda3\lib\site-packages\tensorboard\compat\tensorflow_stubdtypes.py:545: FutureWarning: ν΅κ³Ό(μ ν , 1) μ νμ λμμ΄μΈ '1type'μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. numpyμ ν₯ν λ²μ μμλ (type, (1,)) / '(1,)type'μΌλ‘ μ΄ν΄λ κ²μ λλ€. _np_qint32 = np.dtype([("qint32", np.int32, 1)]) C:\Users\karanbari\Anaconda3\lib\site-packages\tensorboard\compat\tensorflow_stubdtypes.py:550: FutureWarning: ν΅κ³Ό(μ ν , 1) μ νμ λμμ΄μΈ '1type'μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. numpyμ ν₯ν λ²μ μμλ (type, (1,)) / '(1,)type'μΌλ‘ μ΄ν΄λ κ²μ λλ€. np_resource = np.dtype([("resource", np.ubyte, 1)]) κ²½κ³ : νλκ·Έ ꡬ문 λΆμ μ μ λ‘κΉ μ stderrλ‘ μ΄λν©λλ€. W1124 18:22:27.201594 10144 deprecation_wrapper.py:119] C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py:15μμ: tf.train.RMSPropOptimizerλΌλ μ΄λ¦μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. λμ tf.compat.v1.train.RMSPropOptimizerλ₯Ό μ¬μ©νμμμ€. W1124 18:22:27.209591 10144 deprecation_wrapper.py:119] C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py:16μμ: tf.train.AdadeltaOptimizerλΌλ μ΄λ¦μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. λμ tf.compat.v1.train.AdadeltaOptimizerλ₯Ό μ¬μ©νμμμ€. W1124 18:22:27.209591 10144 deprecation_wrapper.py:119] C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py:17μμ: tf.train.AdagradOptimizerλΌλ μ΄λ¦μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. λμ tf.compat.v1.train.AdagradOptimizerλ₯Ό μ¬μ©νμμμ€. W1124 18:22:27.213590 10144 deprecation_wrapper.py:119] C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py:18μμ: tf.train.AdagradDAOptimizerλΌλ μ΄λ¦μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. λμ tf.compat.v1.train.AdagradDAOptimizerλ₯Ό μ¬μ©νμμμ€. W1124 18:22:27.213590 10144 deprecation_wrapper.py:119] C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py:19μμ: tf.train.MomentumOptimizerλΌλ μ΄λ¦μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. λμ tf.compat.v1.train.MomentumOptimizerλ₯Ό μ¬μ©νμμμ€. Parsing ./cfg/tiny-yolo-voc.cfg Parsing cfg/tiny-yolo-voc-1c.cfg Loading bin/tiny-yolo-voc.weights ... 63471556 λ°μ΄νΈλ₯Ό μ±κ³΅μ μΌλ‘ μλ³νμ΅λλ€ 0.019990205764770508s λΉλ© λ€νΈ W1124 18:22:27.253580 10144 deprecation_wrapper.py:119] C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py:105μμ: tf.placeholderλΌλ μ΄λ¦μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. λμ tf.compat.v1.placeholderλ₯Ό μ¬μ©νμΈμ. μΆμ² | κΈ°μ°¨? | λ μ΄μ΄ μ€λͺ | μΆλ ₯ ν¬κΈ° -------+--------+------------------------------ ---+------------ W1124 18:22:27.257580 10144 deprecation_wrapper.py:119] C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\ops\μμ baseop.py:70: tf.variable_scopeλΌλ μ΄λ¦μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. λμ tf.compat.v1.variable_scopeλ₯Ό μ¬μ©νμΈμ. W1124 18:22:27.261598 10144 deprecation_wrapper.py:119] C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\ops\baseop.py:71μμ: tf.get_variable μ΄λ¦μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. λμ tf.compat.v1.get_variableμ μ¬μ©νμμμ€. 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_defaultλΌλ μ΄λ¦μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. λμ tf.compat.v1.placeholder_with_defaultλ₯Ό μ¬μ©νμΈμ. | | μ λ ₯ | (?, 416, 416, 3) λ‘λ | λ€! | conv 3x3p1_1 +bnorm λμ | (?, 416, 416, 16) W1124 18:22:27.389549 10144 deprecation_wrapper.py:119] C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\ops\simple.py:10μμ nn.max_poolμ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. λμ tf.nn.max_pool2dλ₯Ό μ¬μ©νμμμ€. λ‘λ | λ€! | μ΅λ 2x2p0_2 | (?, 208, 208, 16) λ‘λ | λ€! | conv 3x3p1_1 +bnorm λμ | (?, 208, 208, 32) λ‘λ | λ€! | μ΅λ 2x2p0_2 | (?, 104, 104, 32) λ‘λ | λ€! | conv 3x3p1_1 +bnorm λμ | (?, 104, 104, 64) λ‘λ | λ€! | μ΅λ 2x2p0_2 | (?, 52, 52, 64) λ‘λ | λ€! | conv 3x3p1_1 +bnorm λμ | (?, 52, 52, 128) λ‘λ | λ€! | μ΅λ 2x2p0_2 | (?, 26, 26, 128) λ‘λ | λ€! | conv 3x3p1_1 +bnorm λμ | (?, 26, 26, 256) λ‘λ | λ€! | μ΅λ 2x2p0_2 | (?, 13, 13, 256) λ‘λ | λ€! | conv 3x3p1_1 +bnorm λμ | (?, 13, 13, 512) λ‘λ | λ€! | μ΅λ 2x2p0_1 | (?, 13, 13, 512) λ‘λ | λ€! | conv 3x3p1_1 +bnorm λμ | (?, 13, 13, 1024) λ‘λ | λ€! | conv 3x3p1_1 +bnorm λμ | (?, 13, 13, 1024) μ΄κΈ°ν | λ€! | λ³ν 1x1p0_1 μ ν | (?, 13, 13, 30) -------+--------+------------------------ ----------+--------------- CPUμμ μμ ν μ€ν cfg/tiny-yolo-voc-1c.cfg μμ€ νμ΄νΌ 맀κ°λ³μ: H = 13 W = 13 μμ = 5 ν΄λμ€ = 1 μ€μΌμΌ = [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\yolovflowμμ train.py:87: to_float(tensorflow.python.ops.math_opsμμ)λ λ μ΄μ μ¬μ©λμ§ μμΌλ©° ν₯ν λ²μ μμ μ κ±°λ©λλ€. μ λ°μ΄νΈ μ§μΉ¨: λμtf.cast
λ₯Ό μ¬μ©νμΈμ. 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.scalarλΌλ μ΄λ¦μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. λμ tf.compat.v1.summary.scalarλ₯Ό μ¬μ©νμμμ€. 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_opsμμ)λ λ μ΄μ μ¬μ©λμ§ μμΌλ©° ν₯ν λ²μ μμ μ κ±°λ©λλ€. μ λ°μ΄νΈ μ§μΉ¨: np.where W1124 18:22:32.038406 10144 deprecation.py:506] λΈλ‘λμΊμ€νΈ κ·μΉμ΄ λμΌν 2.0μ tf.whereλ₯Ό μ¬μ©νμΈμ. From C:\Users\karanbari\Anaconda3\lib\site-packages\ tensorflow\python\training\rmsprop.py:119: dtypeμ μ¬μ©νμ¬ Ones.__init__(tensorflow.python.ops.init_opsμμ) νΈμΆμ λ μ΄μ μ¬μ©λμ§ μμΌλ©° ν₯ν λ²μ μμ μ κ±°λ©λλ€. μ λ°μ΄νΈ μ§μΉ¨: μμ±μμ μ λ¬νλ λμ dtype μΈμλ‘ μ΄κΈ°ν μΈμ€ν΄μ€λ₯Ό νΈμΆν©λλ€. W1124 18:22:32.795700 10144 deprecation_wrapper.py:119] From C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py :145: tf.Sessionμ΄λΌλ μ΄λ¦μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. λμ tf.compat.v1.Sessionμ μ¬μ©νμμμ€. 2019-11-24 18:22:32.800843: I tensorflow/core/platform/cpu_feature_guard.cc:142] κ·νμ CPUλ μ΄ TensorFlow λ°μ΄λλ¦¬κ° μ¬μ©νλλ‘ μ»΄νμΌλμ§ μμλ€λ λͺ λ Ήμ μ§μν©λλ€. AVX2 Finished in 11.774582862854004cfg Enter training tiny-yolo-voc-1c.cfg parsing annotations_clean ['vodafone']μ λν ꡬ문 λΆμ [===================>]100% Image9.xml ν΅κ³: λ°μ΄ν° μΈνΈ ν¬κΈ° : 53κ° μΈμ€ν΄μ€μ 53κ° λ°μ΄ν° μΈνΈ Image20.jpg μμΆμ (κ°μ₯ μ΅κ·Ό νΈμΆ λ§μ§λ§): νμΌ "flow", μ€ 6, in cliHandler(sys.argv) νμΌ "C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\cli.py", 33ν, cliHandlerμμ print('Enter training ...'); tfnet.train() νμΌ "C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\flow.py", μ€ 39, iμ λν κΈ°μ°¨, (x_batch, datum) in enumerate(λ°°μΉ): νμΌ "C: \Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\yolodata.py", 114ν, μ ν inp, new_feed = self._batch(train_instance) νμΌ "C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\ yolov2data.py", 28ν, _batch img = self.preprocess(path, allobj) νμΌ "C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\yolo\predict.py", 62ν, μ μ²λ¦¬ κ²°κ³Ό = imcv2_affine_trans(im) νμΌ "C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflowutils\im_transform.py", 20ν, imcv2_affine_trans h, w, c = im.shape AttributeError: 'NoneType' κ°μ²΄μ 'shape' μμ±μ΄ μμ΅λλ€. ' β λΉμ μ΄ λκΈμ λ¬μκΈ° λλ¬Έμ μ΄κ²μ λ°λ κ²μ λλ€. λ°λ‘μ΄ μ΄λ©μΌμ νμ GitHubμμμ λ³Ό <# 265? email_source = ν΅μ§ λ° email_token = AGG23MNSSXWIHQFI75KYEWDQVJ3ORA5CNFSM4DNJVSV2YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOEFAKXNA # issuecomment-557886388>, λλ ꡬλ μ·¨μ https://github.com/notifications/unsubscribe-auth/AGG23MMETFBN5NG76IHGWZ3QVJ3ORANCNFSM4DNJVSVQ .
μλμ, Image1, Image2, Image3... λ± νμμ λͺ¨λ μ΄λ―Έμ§λ₯Ό μ¬μ μνμΌλ©° λͺ¨λ μ΄λ―Έμ§μ νμμ .jpgμ λλ€.
μ£Όμ μΉμ μ€ νλκ° λ€μλ³΄λ€ μμ κ°λ₯μ±μ΄ λ§€μ° λμ΅λλ€.
0 λλ μ΄λ―Έμ§μμ λ²μ΄λ¬μ΅λλ€.
λν λͺ¨λ μ΄λ―Έμ§λ₯Ό μλμΌλ‘ μ΄ μ μλμ§ νμΈνμμμ€.
2019λ 11μ 24μΌ μΌμμΌ μ€ν 6μ 42λΆμ karan bari [email protected] μμ λ€μκ³Ό κ°μ΄ μΌμ΅λλ€.
μ΄λ―Έμ§ μ΄λ¦μ νΉμ λ¬Έμκ° μμ΅λκΉ? κ·Έλ λ€λ©΄ λ³κ²½νμμμ€.
β¦ <#m_-6851739743886041955_>
2019λ 11μ 24μΌ μΌμμΌ μ€ν 6μ 32λΆ, karan bari @ . * > μ΄: μλ νμΈμ, μ λ
λ΄ νμ¬ λ‘κ³ λ₯Ό κ°μ§νκΈ° μν΄ μ¬μ©μ μ μ κ°μ²΄ κ°μ§λ₯Ό νλ ¨νλ €κ³ μλν©λλ€.
μ΄ μ€λ₯κΉμ§ λͺ¨λ κ²μ΄ μ μ§νλμμΌλ©° μ΄λ―Έμ§λ μμ νκ³ μ£Όμμ λ¬μμ΅λλ€.
λ€μ λ§νμ§λ§ κ²°κ³Όμλ λ³νκ° μμ΅λλ€. λκ΅°κ° μ΄κ²μ λμμ£ΌμΈμ.
κ°μ¬ν©λλ€(κΈ°λ³Έ) C:\Users\karanbari>cd Desktop/YOLO/darkflow-master(κΈ°λ³Έ)
C:\Users\karanbari\Desktop\YOLOdarkflow-master>python νλ¦ --λͺ¨λΈ
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) λλ '1type'μ typeμ λμμ΄λ‘ μ λ¬νλ©΄
λ μ΄μ μ¬μ©λμ§ μμ numpyμ ν₯ν λ²μ μμλ (μ ν,
(1,)) / '(1,)μ ν'. _np_qint8 = np.dtype([("qint8", np.int8, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\frameworkdtypes.py:517:
FutureWarning: (type, 1) λλ '1type'μ typeμ λμμ΄λ‘ μ λ¬νλ©΄
λ μ΄μ μ¬μ©λμ§ μμ numpyμ ν₯ν λ²μ μμλ (μ ν,
(1,)) / '(1,)μ ν'. _np_quint8 = np.dtype([("quint8", np.uint8, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\frameworkdtypes.py:518:
FutureWarning: (type, 1) λλ '1type'μ typeμ λμμ΄λ‘ μ λ¬νλ©΄
λ μ΄μ μ¬μ©λμ§ μμ numpyμ ν₯ν λ²μ μμλ (μ ν,
(1,)) / '(1,)μ ν'. _np_qint16 = np.dtype([("qint16", np.int16, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\frameworkdtypes.py:519:
FutureWarning: (type, 1) λλ '1type'μ typeμ λμμ΄λ‘ μ λ¬νλ©΄
λ μ΄μ μ¬μ©λμ§ μμ numpyμ ν₯ν λ²μ μμλ (μ ν,
(1,)) / '(1,)μ ν'. _np_quint16 = np.dtype([("quint16", np.uint16, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\frameworkdtypes.py:520:
FutureWarning: (type, 1) λλ '1type'μ typeμ λμμ΄λ‘ μ λ¬νλ©΄
λ μ΄μ μ¬μ©λμ§ μμ numpyμ ν₯ν λ²μ μμλ (μ ν,
(1,)) / '(1,)μ ν'. _np_qint32 = np.dtype([("qint32", np.int32, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorflow\python\frameworkdtypes.py:525:
FutureWarning: (type, 1) λλ '1type'μ typeμ λμμ΄λ‘ μ λ¬νλ©΄
λ μ΄μ μ¬μ©λμ§ μμ numpyμ ν₯ν λ²μ μμλ (μ ν,
(1,)) / '(1,)μ ν'. np_resource = np.dtype([("리μμ€", np.ubyte, 1)])
C:\Users\karanbari\Anaconda3\lib\site-packages\tensorboard\compat\tensorflow_stubdtypes.py:541:
FutureWarning: (type, 1) λλ '1type'μ typeμ λμμ΄λ‘ μ λ¬νλ©΄
λ μ΄μ μ¬μ©λμ§ μμ numpyμ ν₯ν λ²μ μμλ (μ ν,
(1,)) / '(1,)μ 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) λλ '1type'μ typeμ λμμ΄λ‘ μ λ¬νλ©΄
λ μ΄μ μ¬μ©λμ§ μμ numpyμ ν₯ν λ²μ μμλ (μ ν,
(1,)) / '(1,)μ 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) λλ '1type'μ typeμ λμμ΄λ‘ μ λ¬νλ©΄
λ μ΄μ μ¬μ©λμ§ μμ numpyμ ν₯ν λ²μ μμλ (μ ν,
(1,)) / '(1,)μ 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) λλ '1type'μ typeμ λμμ΄λ‘ μ λ¬νλ©΄
λ μ΄μ μ¬μ©λμ§ μμ numpyμ ν₯ν λ²μ μμλ (μ ν,
(1,)) / '(1,)μ 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) λλ '1type'μ typeμ λμμ΄λ‘ μ λ¬νλ©΄
λ μ΄μ μ¬μ©λμ§ μμ numpyμ ν₯ν λ²μ μμλ (μ ν,
(1,)) / '(1,)μ 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) λλ '1type'μ typeμ λμμ΄λ‘ μ λ¬νλ©΄
λ μ΄μ μ¬μ©λμ§ μμ numpyμ ν₯ν λ²μ μμλ (μ ν,
(1,)) / '(1,)μ ν'. np_resource = np.dtype([("리μμ€", np.ubyte, 1)])
κ²½κ³ : νλκ·Έ ꡬ문 λΆμ μ μ λ‘κΉ μ stderrλ‘ μ΄λν©λλ€. W1124 18:22:27.201594
10144 deprecation_wrapper.py:119] λ°μ μ
C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py:15:
tf.train.RMSPropOptimizerλΌλ μ΄λ¦μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. μ¬μ©νμμμ€
λμ tf.compat.v1.train.RMSPropOptimizer. W1124 18:22:27.209591 10144
deprecation_wrapper.py:119] λ°μ μ
C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py:16:
tf.train.AdadeltaOptimizerλΌλ μ΄λ¦μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. μ¬μ©νμμμ€
λμ tf.compat.v1.train.AdadeltaOptimizer. W1124 18:22:27.209591 10144
deprecation_wrapper.py:119] λ°μ μ
C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py:17:
tf.train.AdagradOptimizerλΌλ μ΄λ¦μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. μ¬μ©νμμμ€
λμ tf.compat.v1.train.AdagradOptimizer. W1124 18:22:27.213590 10144
deprecation_wrapper.py:119] λ°μ μ
C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py:18:
tf.train.AdagradDAOptimizerλΌλ μ΄λ¦μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. μ¬μ©νμμμ€
λμ tf.compat.v1.train.AdagradDAOptimizer. W1124 18:22:27.213590 10144
deprecation_wrapper.py:119] λ°μ μ
C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py:19:
tf.train.MomentumOptimizerλΌλ μ΄λ¦μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. μ¬μ©νμμμ€
λμ tf.compat.v1.train.MomentumOptimizer. νμ±
./cfg/tiny-yolo-voc.cfg νμ± cfg/tiny-yolo-voc-1c.cfg λ‘λ©
bin/tiny-yolo-voc.weights ... μ±κ³΅μ μΌλ‘ μλ³λ 63471556λ°μ΄νΈ
Finished in 0.019990205764770508s λΉλ©λ· ... W1124 18:22:27.253580
10144 deprecation_wrapper.py:119] λ°μ μ
C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py:105:
tf.placeholderλΌλ μ΄λ¦μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. tf.compat.v1.placeholderλ₯Ό μ¬μ©νμΈμ.
λμ μ. μΆμ² | κΈ°μ°¨? | λ μ΄μ΄ μ€λͺ | μΆλ ₯ ν¬κΈ°
-------+--------+--------------------------------- ------------------- W1124
18:22:27.257580 10144 deprecation_wrapper.py:119] λ°μ μ
C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\ops\baseop.py:70:
tf.variable_scopeλΌλ μ΄λ¦μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. μ¬μ©νμμμ€
λμ tf.compat.v1.variable_scope. W1124 18:22:27.261598 10144
deprecation_wrapper.py:119] λ°μ μ
C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\ops\baseop.py:71:
tf.get_variableμ΄λΌλ μ΄λ¦μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. μ¬μ©νμμμ€
λμ tf.compat.v1.get_variable. W1124 18:22:27.277594 10144
deprecation_wrapper.py:119] λ°μ μ
C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\ops\baseop.py:84:
tf.placeholder_with_defaultλΌλ μ΄λ¦μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. μ¬μ©νμμμ€
λμ tf.compat.v1.placeholder_with_default. | | μ λ ₯ | (?, 416, 416, 3)
λ‘λ | λ€! | conv 3x3p1_1 +bnorm λμ | (?, 416, 416, 16) W1124
18:22:27.389549 10144 deprecation_wrapper.py:119] λ°μ μ
C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\ops\simple.py:106:
tf.nn.max_poolμ΄λΌλ μ΄λ¦μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. λμ tf.nn.max_pool2dλ₯Ό μ¬μ©νμμμ€.
λ‘λ | λ€! | μ΅λ 2x2p0_2 | (?, 208, 208, 16) λ‘λ | λ€! | μ ν 3x3p1_1
+bnorm μλ | (?, 208, 208, 32) λ‘λ | λ€! | μ΅λ 2x2p0_2 | (?, 104, 104,
32) λ‘λ | λ€! | conv 3x3p1_1 +bnorm λμ | (?, 104, 104, 64) λ‘λ | λ€!
| μ΅λ 2x2p0_2 | (?, 52, 52, 64) λ‘λ | λ€! | conv 3x3p1_1 +bnorm λμ |
(?, 52, 52, 128) λ‘λ | λ€! | μ΅λ 2x2p0_2 | (?, 26, 26, 128) λ‘λ | λ€!
| conv 3x3p1_1 +bnorm λμ | (?, 26, 26, 256) λ‘λ | λ€! | μ΅λ 2x2p0_2 |
(?, 13, 13, 256) λ‘λ | λ€! | conv 3x3p1_1 +bnorm λμ | (?, 13, 13, 512)
λ‘λ | λ€! | μ΅λ 2x2p0_1 | (?, 13, 13, 512) λ‘λ | λ€! | μ ν 3x3p1_1
+bnorm μλ | (?, 13, 13, 1024) λ‘λ | λ€! | conv 3x3p1_1 +bnorm λμ |
(?, 13, 13, 1024) μ΄κΈ°ν | λ€! | λ³ν 1x1p0_1 μ ν | (?, 13, 13, 30)
-------+--------+--------------------------------- ------------------- μ€ν μ€
μ μ μΌλ‘ CPUμ cfg/tiny-yolo-voc-1c.cfg μμ€ νμ΄νΌ 맀κ°λ³μ: H = 13 W =
13 μμ = 5 ν΄λμ€ = 1 μ μΈ = [1.0, 5.0, 1.0, 1.0] W1124 18:22:29.962576
10144 deprecation.py:323] λ°μ μ
C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\yolov2\train.py:87:
to_float(tensorflow.python.ops.math_opsμμ)λ λ μ΄μ μ¬μ©λμ§ μμΌλ©° μμΌλ‘λ
ν₯ν λ²μ μμ μ κ±°λ©λλ€. μ λ°μ΄νΈ μ§μΉ¨: tf.cast μ¬μ©
λμ μ. λΉλ© cfg/tiny-yolo-voc-1c.cfg loss W1124 18:22:30.010835 10144
deprecation_wrapper.py:119] λ°μ μ
C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\yolov2\train.py:107:
tf.summary.scalarλΌλ μ΄λ¦μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. μ¬μ©νμμμ€
λμ tf.compat.v1.summary.scalar. cfg/tiny-yolo-voc-1c.cfg ꡬμΆ
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_opsμμ)λ
λ μ΄μ μ¬μ©λμ§ μμΌλ©° ν₯ν λ²μ μμ μ κ±°λ©λλ€. μ§μΉ¨
μ λ°μ΄νΈ: λΈλ‘λμΊμ€νΈ κ·μΉμ΄ λμΌν 2.0μμ tf.whereλ₯Ό μ¬μ©ν©λλ€.
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:
μμ νΈμΆν©λλ€. dtypeμ΄ μλ init (tensorflow.python.ops.init_opsμμ)λ λ€μκ³Ό κ°μ΅λλ€.
λ μ΄μ μ¬μ©λμ§ μμΌλ©° ν₯ν λ²μ μμ μ κ±°λ©λλ€. μ§μΉ¨
μ λ°μ΄νΈ: λμ dtype μΈμλ₯Ό μ¬μ©νμ¬ μ΄κΈ°ν μΈμ€ν΄μ€λ₯Ό νΈμΆν©λλ€.
μμ±μμ μ λ¬ W1124 18:22:32.795700 10144
deprecation_wrapper.py:119] λ°μ μ
C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\build.py:145:
tf.Sessionμ΄λΌλ μ΄λ¦μ λ μ΄μ μ¬μ©λμ§ μμ΅λλ€. λμ tf.compat.v1.Sessionμ μ¬μ©νμμμ€.
2019-11-24 18:22:32.800843: λ
tensorflow/core/platform/cpu_feature_guard.cc:142] CPU μ§μ
μ΄ TensorFlow λ°μ΄λλ¦¬κ° μ¬μ©νλλ‘ μ»΄νμΌλμ§ μμ λͺ λ Ή: AVX2
11.774582862854004sμμ μλ£ κ΅μ‘ μμ ... cfg/tiny-yolo-voc-1c.cfg
ꡬ문 λΆμ annotations_clean ['vodafone']μ λν ꡬ문 λΆμ
[=====================>]100% Image9.xml ν΅κ³: λ°μ΄ν° μΈνΈ ν¬κΈ°: 53 λ°μ΄ν° μΈνΈ
53κ° μΈμ€ν΄μ€ μ€ Image20.jpg μμΆμ (κ°μ₯ μ΅κ·Ό νΈμΆ λ§μ§λ§): νμΌ
"flow", 6ν, cliHandler(sys.argv) νμΌ
"C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\cli.py", 33ν,
in cliHandler print('νλ ¨ μ λ ₯ ...'); tfnet.train() νμΌ
"C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\flow.py",
39ν, in train for i, (x_batch, datum) in enumerate(batch): νμΌ
"C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\yolodata.py",
114ν, μ ν inpμμ new_feed = self._batch(train_instance) νμΌ
"C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\yolov2data.py",
28ν, _batch img = self.preprocess(κ²½λ‘, allobj) νμΌ
"C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflow\net\yolo\predict.py",
62ν, μ μ²λ¦¬ κ²°κ³Ό = imcv2_affine_trans(im) νμΌ
"C:\Users\karanbari\Desktop\YOLOdarkflow-masterdarkflowutils\im_transform.py",
20ν, imcv2_affine_trans h, w, c = im.shape AttributeError:
'NoneType' κ°μ²΄μλ 'shape' μμ±μ΄ μμ΅λλ€.
λΉμ μ λκΈμ λ¬μμ΅λλ€. μ΄ μ΄λ©μΌμ μ§μ λ΅μ₯νκ³ GitHub <#265μμ νμΈνμΈμ.
https://github.com/thtrieu/darkflow/issues/265 ?email_source=notifications&email_token=AGG23MNSSXWIHQFI75KYEWDQVJ3ORA5CNFSM4DNJVSV2YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63
λλ ꡬλ μ·¨μ
https://github.com/notifications/unsubscribe-auth/AGG23MMETFBN5NG76IHGWZ3QVJ3ORANCNFSM4DNJVSVQ
.μλμ, Image1, Image2, Image3... λ± νμμ λͺ¨λ μ΄λ―Έμ§λ₯Ό λ€μ μ¬μ©νμ΅λλ€.
λͺ¨λ μ΄λ―Έμ§μλ .jpg νμμ΄ μμ΅λλ€.β
λΉμ μ΄ λκΈμ λ¬μκΈ° λλ¬Έμ μ΄κ²μ λ°λ κ²μ λλ€.
μ΄ μ΄λ©μΌμ μ§μ λ΅μ₯νκ³ GitHubμμ νμΈνμΈμ.
https://github.com/thtrieu/darkflow/issues/265?email_source=notifications&email_token=AGG23MJ2SKBIF2FQTPTLBRLQVJ4SVA5CNFSM4DNJVSV2YY3PNVWWK3TUL52HS4DFVEXG43VMVBW63
λλ ꡬλ μ·¨μ
https://github.com/notifications/unsubscribe-auth/AGG23ML6HYW6S7JZEN2ZAF3QVJ4SVANCNFSM4DNJVSVQ
.
μ΄λ²μλ labelImgλ₯Ό μ¬μ©νμ¬ μ΄λ―Έμ§μ λ€μ μ£Όμμ λ¬μμ§λ§ λ¬Έμ λ μ¬μ ν μ§μλ©λλ€.
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'
μ¬κΈ°μ λ€μ μ€λ₯κ° μκ³ Image7.jpgμ λν ν΄λΉ .xml νμΌμ΄ μμ΅λλ€.
<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£Όλκ² λ«λ€
print(im, type(im))
L58μ darkflow/net/yolo/predict.pyμμ μ§μ κ²½λ‘λ₯Ό νμΈνμμμ€.
κ°μ μ€λ₯κ° λ°μνμ΅λλ€
λλ κ°μ λ¬Έμ μ μ§λ©΄νκ³ λ΄ μμ μ¬νμ λ€μκ³Ό κ°μ΅λλ€.
predict.py λΌμΈ# 60μμ im = cv2.imread(im) μ im = cv2.imread(im+'.jpg') λ‘ λ³κ²½νμ΅λλ€.
λλ κ°μ λ¬Έμ κ° μμκ³ jpg μ΄λ―Έμ§λ₯Ό μμ νμ§λ§ μ£Όμμ μμ νλ κ²μ μμκΈ° λλ¬Έμ λλ€. λ°λΌμ μ΄λ―Έμ§μ μ£Όμμ΄ μΌκ΄μ±μ΄ μλμ§ νμΈνμμμ€.
κ°μ₯ μ μ©ν λκΈ
λλ κ³Όκ±°μ μ΄κ²μ λ§λ¬λ€. μΌλΆ
.xml
λλ.jpg
νμΌμ΄ μ λλ‘ λͺ λͺ /ꡬμ±λμ§ μμμ κ°λ₯μ±μ΄ λμ΅λλ€. 무μμ΄ μλͺ»λμλμ§ λλ²κΉ νλ ν κ°μ§ λ°©λ²μ λ€μμ μΆκ°νλ κ²μ λλ€.μ΄ μ€ μ΄ν: https://github.com/thtrieu/darkflow/blob/master/darkflow/net/yolov2/data.py#L26
λ°λΌμ μμλ νμΌμ μ΄λ¦μ 보κ³
.xml
λλ.jpg
μ€ νλλ₯Ό μ‘°μ¬ν μ μμ΅λλ€.