Easy training on custom dataset. Various backends (MobileNet and SqueezeNet) supported. A YOLO demo to detect raccoon run entirely in brower is accessible at https://git.io/vF7vI (not on Windows).
My code was running before, then i upgraded tensorflow gpu then i removed it and installed it again then i'm facing the following bug.
Any suggestion?
FutureWarning: Conversion of the second argument of issubdtype from float to np.floating is deprecated. In future, it will be treated as np.float64 == np.dtype(float).type.
from ._conv import register_converters as _register_converters
Using TensorFlow backend.
2018-09-27 09:46:23.817020: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2018-09-27 09:46:23.902773: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:892] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2018-09-27 09:46:23.903070: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1030] Found device 0 with properties:
name: TITAN X (Pascal) major: 6 minor: 1 memoryClockRate(GHz): 1.531
pciBusID: 0000:01:00.0
totalMemory: 11.91GiB freeMemory: 11.59GiB
2018-09-27 09:46:23.903091: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1120] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: TITAN X (Pascal), pci bus id: 0000:01:00.0, compute capability: 6.1)
[[22. 28.]
[49. 64.]]
('Seen labels:\t', {'positive': 12515, 'negative': 47680})
('Given labels:\t', [u'positive', u'negative'])
('Overlap labels:\t', set(['positive', 'negative']))
2018-09-27 09:46:37.048729: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1120] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: TITAN X (Pascal), pci bus id: 0000:01:00.0, compute capability: 6.1)
(13, 13)
Total params: 50,583,811
Trainable params: 50,563,139
Non-trainable params: 20,672
Total params: 50,583,811
Trainable params: 50,563,139
Non-trainable params: 20,672
Epoch 1/4
Traceback (most recent call last):
File "train.py", line 110, in main(args)
File "train.py", line 106, in main
debug = config['train']['debug'])
File "/home/*/Yolo/keras-yolo2/frontend.py", line 336, in train
max_queue_size = 8)
File "/home/***/anaconda2/envs/Py27/lib/python2.7/site-packages/keras/legacy/interfaces.py", line 91, in wrapper
return func(args, kwargs)
File "/home//anaconda2/envs/Py27/lib/python2.7/site-packages/keras/engine/training.py", line 1415, in fit_generator
initial_epoch=initial_epoch)
File "/home//anaconda2/envs/Py27/lib/python2.7/site-packages/keras/engine/training_generator.py", line 177, in fit_generator
generator_output = next(output_generator)
File "/home//anaconda2/envs/Py27/lib/python2.7/site-packages/keras/utils/data_utils.py", line 584, in get
six.raise_from(StopIteration(e), e)
File "/home//anaconda2/envs/Py27/lib/python2.7/site-packages/six.py", line 737, in raise_from
raise value
StopIteration: 'IMAGE_C'
Hi,
My code was running before, then i upgraded tensorflow gpu then i removed it and installed it again then i'm facing the following bug.
Any suggestion?
FutureWarning: Conversion of the second argument of issubdtype from
floattonp.floatingis deprecated. In future, it will be treated asnp.float64 == np.dtype(float).type. from ._conv import register_converters as _register_converters Using TensorFlow backend. 2018-09-27 09:46:23.817020: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA 2018-09-27 09:46:23.902773: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:892] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2018-09-27 09:46:23.903070: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1030] Found device 0 with properties: name: TITAN X (Pascal) major: 6 minor: 1 memoryClockRate(GHz): 1.531 pciBusID: 0000:01:00.0 totalMemory: 11.91GiB freeMemory: 11.59GiB 2018-09-27 09:46:23.903091: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1120] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: TITAN X (Pascal), pci bus id: 0000:01:00.0, compute capability: 6.1) [[22. 28.] [49. 64.]] ('Seen labels:\t', {'positive': 12515, 'negative': 47680}) ('Given labels:\t', [u'positive', u'negative']) ('Overlap labels:\t', set(['positive', 'negative'])) 2018-09-27 09:46:37.048729: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1120] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: TITAN X (Pascal), pci bus id: 0000:01:00.0, compute capability: 6.1) (13, 13)Layer (type) Output Shape Param # Connected to
input_1 (InputLayer) (None, 416, 416, 3) 0
model_1 (Model) (None, 13, 13, 1024) 50547936 input_1[0][0]
DetectionLayer (Conv2D) (None, 13, 13, 35) 35875 model_1[1][0]
reshape_1 (Reshape) (None, 13, 13, 5, 7) 0 DetectionLayer[0][0]
input_2 (InputLayer) (None, 1, 1, 1, 10, 0
lambda_2 (Lambda) (None, 13, 13, 5, 7) 0 reshape_1[0][0] input_2[0][0]
Total params: 50,583,811 Trainable params: 50,563,139 Non-trainable params: 20,672
Total params: 50,583,811 Trainable params: 50,563,139 Non-trainable params: 20,672
Epoch 1/4 Traceback (most recent call last): File "train.py", line 110, in
main(args)
File "train.py", line 106, in main
debug = config['train']['debug'])
File "/home/*/Yolo/keras-yolo2/frontend.py", line 336, in train
max_queue_size = 8)
File "/home/***/anaconda2/envs/Py27/lib/python2.7/site-packages/keras/legacy/interfaces.py", line 91, in wrapper
return func(args, kwargs)
File "/home//anaconda2/envs/Py27/lib/python2.7/site-packages/keras/engine/training.py", line 1415, in fit_generator
initial_epoch=initial_epoch)
File "/home//anaconda2/envs/Py27/lib/python2.7/site-packages/keras/engine/training_generator.py", line 177, in fit_generator
generator_output = next(output_generator)
File "/home//anaconda2/envs/Py27/lib/python2.7/site-packages/keras/utils/data_utils.py", line 584, in get
six.raise_from(StopIteration(e), e)
File "/home//anaconda2/envs/Py27/lib/python2.7/site-packages/six.py", line 737, in raise_from
raise value
StopIteration: 'IMAGE_C'