質問編集履歴
2
書式の改善
title
CHANGED
File without changes
|
body
CHANGED
@@ -1,6 +1,6 @@
|
|
1
1
|
Windows 10 で YOLOv3 を自前画像で学習させることを行っていますが以下のエラーが出てしまいました。助けてください。
|
2
2
|
|
3
|
-
(tf114) C:\
|
3
|
+
(tf114) C:\keras-yolo3\keras-yolo3-master>python train.py
|
4
4
|
Using TensorFlow backend.
|
5
5
|
C:\Users\std09\Anaconda3\envs\tf114\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'.
|
6
6
|
_np_qint8 = np.dtype([("qint8", np.int8, 1)])
|
@@ -26,16 +26,73 @@
|
|
26
26
|
_np_qint32 = np.dtype([("qint32", np.int32, 1)])
|
27
27
|
C:\Users\std09\Anaconda3\envs\tf114\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'.
|
28
28
|
np_resource = np.dtype([("resource", np.ubyte, 1)])
|
29
|
+
WARNING:tensorflow:From C:\Users\std09\Anaconda3\envs\tf114\lib\site-packages\keras\backend\tensorflow_backend.py:95: The name tf.reset_default_graph is deprecated. Please use tf.compat.v1.reset_default_graph instead.
|
30
|
+
|
31
|
+
WARNING:tensorflow:From C:\Users\std09\Anaconda3\envs\tf114\lib\site-packages\keras\backend\tensorflow_backend.py:98: The name tf.placeholder_with_default is deprecated. Please use tf.compat.v1.placeholder_with_default instead.
|
32
|
+
|
33
|
+
WARNING:tensorflow:From C:\Users\std09\Anaconda3\envs\tf114\lib\site-packages\keras\backend\tensorflow_backend.py:102: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead.
|
34
|
+
|
35
|
+
WARNING:tensorflow:From C:\Users\std09\Anaconda3\envs\tf114\lib\site-packages\keras\backend\tensorflow_backend.py:174: The name tf.get_default_session is deprecated. Please use tf.compat.v1.get_default_session instead.
|
36
|
+
|
37
|
+
WARNING:tensorflow:From C:\Users\std09\Anaconda3\envs\tf114\lib\site-packages\keras\backend\tensorflow_backend.py:181: The name tf.ConfigProto is deprecated. Please use tf.compat.v1.ConfigProto instead.
|
38
|
+
|
39
|
+
2021-02-16 14:07:39.385171: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2
|
40
|
+
2021-02-16 14:07:39.389988: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library nvcuda.dll
|
41
|
+
2021-02-16 14:07:39.392874: E tensorflow/stream_executor/cuda/cuda_driver.cc:318] failed call to cuInit: CUDA_ERROR_UNKNOWN: unknown error
|
42
|
+
2021-02-16 14:07:39.397734: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:169] retrieving CUDA diagnostic information for host: ELNET09
|
43
|
+
2021-02-16 14:07:39.399635: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:176] hostname: ELNET09
|
44
|
+
WARNING:tensorflow:From C:\Users\std09\Anaconda3\envs\tf114\lib\site-packages\keras\backend\tensorflow_backend.py:1919: The name tf.nn.fused_batch_norm is deprecated. Please use tf.compat.v1.nn.fused_batch_norm instead.
|
45
|
+
|
46
|
+
Create YOLOv3 model with 9 anchors and 2 classes.
|
47
|
+
C:\Users\std09\Anaconda3\envs\tf114\lib\site-packages\keras\engine\saving.py:1140: UserWarning: Skipping loading of weights for layer conv2d_59 due to mismatch in shape ((1, 1, 1024, 21) vs (255, 1024, 1, 1)).
|
48
|
+
weight_values[i].shape))
|
49
|
+
C:\Users\std09\Anaconda3\envs\tf114\lib\site-packages\keras\engine\saving.py:1140: UserWarning: Skipping loading of weights for layer conv2d_59 due to mismatch in shape ((21,) vs (255,)).
|
50
|
+
weight_values[i].shape))
|
51
|
+
C:\Users\std09\Anaconda3\envs\tf114\lib\site-packages\keras\engine\saving.py:1140: UserWarning: Skipping loading of weights for layer conv2d_67 due to mismatch in shape ((1, 1, 512, 21) vs (255, 512, 1, 1)).
|
52
|
+
weight_values[i].shape))
|
53
|
+
C:\Users\std09\Anaconda3\envs\tf114\lib\site-packages\keras\engine\saving.py:1140: UserWarning: Skipping loading of weights for layer conv2d_67 due to mismatch in shape ((21,) vs (255,)).
|
54
|
+
weight_values[i].shape))
|
55
|
+
C:\Users\std09\Anaconda3\envs\tf114\lib\site-packages\keras\engine\saving.py:1140: UserWarning: Skipping loading of weights for layer conv2d_75 due to mismatch in shape ((1, 1, 256, 21) vs (255, 256, 1, 1)).
|
56
|
+
weight_values[i].shape))
|
57
|
+
C:\Users\std09\Anaconda3\envs\tf114\lib\site-packages\keras\engine\saving.py:1140: UserWarning: Skipping loading of weights for layer conv2d_75 due to mismatch in shape ((21,) vs (255,)).
|
58
|
+
weight_values[i].shape))
|
59
|
+
Load weights model_data/yolo_weights.h5.
|
60
|
+
Freeze the first 249 layers of total 252 layers.
|
61
|
+
WARNING:tensorflow:From C:\Users\std09\Anaconda3\envs\tf114\lib\site-packages\keras\backend\tensorflow_backend.py:3080: add_dispatch_support.<locals>.wrapper (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.
|
62
|
+
Instructions for updating:
|
63
|
+
Use tf.where in 2.0, which has the same broadcast rule as np.where
|
64
|
+
Train on 42 samples, val on 4 samples, with batch size 32.
|
65
|
+
Epoch 1/50
|
29
66
|
Traceback (most recent call last):
|
30
67
|
File "train.py", line 190, in <module>
|
31
68
|
_main()
|
32
|
-
File "train.py", line
|
69
|
+
File "train.py", line 65, in _main
|
33
|
-
freeze_body=2, weights_path='model_data/yolo_weights.h5') # make sure you know what you freeze
|
34
|
-
File "train.py", line 108, in create_model
|
35
|
-
|
70
|
+
callbacks=[logging, checkpoint])
|
36
|
-
File "C:\Users\std09\Anaconda3\envs\tf114\lib\site-packages\keras\
|
71
|
+
File "C:\Users\std09\Anaconda3\envs\tf114\lib\site-packages\keras\legacy\interfaces.py", line 91, in wrapper
|
72
|
+
return func(*args, **kwargs)
|
73
|
+
File "C:\Users\std09\Anaconda3\envs\tf114\lib\site-packages\keras\engine\training.py", line 1418, in fit_generator
|
74
|
+
initial_epoch=initial_epoch)
|
75
|
+
File "C:\Users\std09\Anaconda3\envs\tf114\lib\site-packages\keras\engine\training_generator.py", line 181, in fit_generator
|
37
|
-
|
76
|
+
generator_output = next(output_generator)
|
77
|
+
File "C:\Users\std09\Anaconda3\envs\tf114\lib\site-packages\keras\utils\data_utils.py", line 709, in get
|
78
|
+
six.reraise(*sys.exc_info())
|
79
|
+
File "C:\Users\std09\Anaconda3\envs\tf114\lib\site-packages\six.py", line 703, in reraise
|
80
|
+
raise value
|
81
|
+
File "C:\Users\std09\Anaconda3\envs\tf114\lib\site-packages\keras\utils\data_utils.py", line 685, in get
|
82
|
+
inputs = self.queue.get(block=True).get()
|
83
|
+
File "C:\Users\std09\Anaconda3\envs\tf114\lib\multiprocessing\pool.py", line 657, in get
|
84
|
+
raise self._value
|
85
|
+
File "C:\Users\std09\Anaconda3\envs\tf114\lib\multiprocessing\pool.py", line 121, in worker
|
86
|
+
result = (True, func(*args, **kwds))
|
87
|
+
File "C:\Users\std09\Anaconda3\envs\tf114\lib\site-packages\keras\utils\data_utils.py", line 626, in next_sample
|
88
|
+
return six.next(_SHARED_SEQUENCES[uid])
|
38
|
-
|
89
|
+
File "train.py", line 175, in data_generator
|
39
|
-
|
90
|
+
image, box = get_random_data(annotation_lines[i], input_shape, random=True)
|
91
|
+
File "C:\keras-yolo3\keras-yolo3-master\yolo3\utils.py", line 39, in get_random_data
|
92
|
+
image = Image.open(line[0])
|
93
|
+
File "C:\Users\std09\Anaconda3\envs\tf114\lib\site-packages\PIL\Image.py", line 2904, in open
|
94
|
+
fp = builtins.open(filename, "rb")
|
95
|
+
FileNotFoundError: [Errno 2] No such file or directory: 'image_015'
|
96
|
+
最後のエラーはやるたびにimage_015の数字が変わります。
|
40
97
|
[参考文献]
|
41
98
|
https://rightcode.co.jp/blog/information-technology/learn-yolov3-image-windows10-environment-construction#_YOLOv3
|
1
書式の改善
title
CHANGED
File without changes
|
body
CHANGED
@@ -35,6 +35,7 @@
|
|
35
35
|
K.clear_session() # get a new session
|
36
36
|
File "C:\Users\std09\Anaconda3\envs\tf114\lib\site-packages\keras\backend\tensorflow_backend.py", line 102, in clear_session
|
37
37
|
_GRAPH_LEARNING_PHASES[tf.compat.v1.get_default_graph] = phase
|
38
|
+
NameError: name 'phase' is not defined
|
38
39
|
|
39
40
|
[参考文献]
|
40
41
|
https://rightcode.co.jp/blog/information-technology/learn-yolov3-image-windows10-environment-construction#_YOLOv3
|