Better training time using GTX 1050 than GTX TITAN X? (4GB vs. 12GB). Why I get CPU times in history? [on...
$begingroup$
I have 2 computers:
First with GTX1050:
Epoch 1/1
200/200 [==============================] - 490s 2s/step - loss: 1.8045 - rpn_class_loss: 0.0629 - rpn_bbox_loss: 0.4044 - mrcnn_class_loss: 0.3132 - mrcnn_bbox_loss: 0.5639 - mrcnn_mask_loss: 0.4601 - val_loss: 2.6684 - val_rpn_class_loss: 0.0712 - val_rpn_bbox_loss: 1.0801 - val_mrcnn_class_loss: 0.3276 - val_mrcnn_bbox_loss: 0.6830 - val_mrcnn_mask_loss: 0.5066
CPU times: user 12min 22s, sys: 29.9 s, total: 12min 51s
Wall time: 8min 40s
Second with GTX TITAN X:
Epoch 1/1
200/200 [==============================] - 461s 2s/step - loss: 1.7415 - rpn_class_loss: 0.0592 - rpn_bbox_loss: 0.4563 - mrcnn_class_loss: 0.2490 - mrcnn_bbox_loss: 0.5253 - mrcnn_mask_loss: 0.4517 - val_loss: 1.9419 - val_rpn_class_loss: 0.0657 - val_rpn_bbox_loss: 0.6273 - val_mrcnn_class_loss: 0.2827 - val_mrcnn_bbox_loss: 0.5468 - val_mrcnn_mask_loss: 0.4194
CPU times: user 4min 34s, sys: 7.73 s, total: 4min 42s
Wall time: 10min 32s
What is it CPU times? I use tensorflow-gpu... Should be GPU-times?
What is going on?
network: Mask RCNN
Keras version: 2.2.4
Tensorflow version: 1.12.0
CUDA Version 9.0.176
cudnn 7.0.5
machine-learning deep-learning tensorflow cnn gpu
asked 9 hours ago
BadumBadum
487
$endgroup$
put on hold as unclear what you're asking by D.W., Dawny33♦ 7 hours ago
Please clarify your specific problem or add additional details to highlight exactly what you need. As it's currently written, it’s hard to tell exactly what you're asking. See the How to Ask page for help clarifying this question. If this question can be reworded to fit the rules in the help center, please edit the question.
add a comment |
$begingroup$
I have 2 computers:
First with GTX1050:
Epoch 1/1
200/200 [==============================] - 490s 2s/step - loss: 1.8045 - rpn_class_loss: 0.0629 - rpn_bbox_loss: 0.4044 - mrcnn_class_loss: 0.3132 - mrcnn_bbox_loss: 0.5639 - mrcnn_mask_loss: 0.4601 - val_loss: 2.6684 - val_rpn_class_loss: 0.0712 - val_rpn_bbox_loss: 1.0801 - val_mrcnn_class_loss: 0.3276 - val_mrcnn_bbox_loss: 0.6830 - val_mrcnn_mask_loss: 0.5066
CPU times: user 12min 22s, sys: 29.9 s, total: 12min 51s
Wall time: 8min 40s
Second with GTX TITAN X:
Epoch 1/1
200/200 [==============================] - 461s 2s/step - loss: 1.7415 - rpn_class_loss: 0.0592 - rpn_bbox_loss: 0.4563 - mrcnn_class_loss: 0.2490 - mrcnn_bbox_loss: 0.5253 - mrcnn_mask_loss: 0.4517 - val_loss: 1.9419 - val_rpn_class_loss: 0.0657 - val_rpn_bbox_loss: 0.6273 - val_mrcnn_class_loss: 0.2827 - val_mrcnn_bbox_loss: 0.5468 - val_mrcnn_mask_loss: 0.4194
CPU times: user 4min 34s, sys: 7.73 s, total: 4min 42s
Wall time: 10min 32s
What is it CPU times? I use tensorflow-gpu... Should be GPU-times?
What is going on?
network: Mask RCNN
Keras version: 2.2.4
Tensorflow version: 1.12.0
CUDA Version 9.0.176
cudnn 7.0.5
machine-learning deep-learning tensorflow cnn gpu
asked 9 hours ago
BadumBadum
487
$endgroup$
put on hold as unclear what you're asking by D.W., Dawny33♦ 7 hours ago
Please clarify your specific problem or add additional details to highlight exactly what you need. As it's currently written, it’s hard to tell exactly what you're asking. See the How to Ask page for help clarifying this question. If this question can be reworded to fit the rules in the help center, please edit the question.
add a comment |
$begingroup$
I have 2 computers:
First with GTX1050:
Epoch 1/1
200/200 [==============================] - 490s 2s/step - loss: 1.8045 - rpn_class_loss: 0.0629 - rpn_bbox_loss: 0.4044 - mrcnn_class_loss: 0.3132 - mrcnn_bbox_loss: 0.5639 - mrcnn_mask_loss: 0.4601 - val_loss: 2.6684 - val_rpn_class_loss: 0.0712 - val_rpn_bbox_loss: 1.0801 - val_mrcnn_class_loss: 0.3276 - val_mrcnn_bbox_loss: 0.6830 - val_mrcnn_mask_loss: 0.5066
CPU times: user 12min 22s, sys: 29.9 s, total: 12min 51s
Wall time: 8min 40s
Second with GTX TITAN X:
Epoch 1/1
200/200 [==============================] - 461s 2s/step - loss: 1.7415 - rpn_class_loss: 0.0592 - rpn_bbox_loss: 0.4563 - mrcnn_class_loss: 0.2490 - mrcnn_bbox_loss: 0.5253 - mrcnn_mask_loss: 0.4517 - val_loss: 1.9419 - val_rpn_class_loss: 0.0657 - val_rpn_bbox_loss: 0.6273 - val_mrcnn_class_loss: 0.2827 - val_mrcnn_bbox_loss: 0.5468 - val_mrcnn_mask_loss: 0.4194
CPU times: user 4min 34s, sys: 7.73 s, total: 4min 42s
Wall time: 10min 32s
What is it CPU times? I use tensorflow-gpu... Should be GPU-times?
What is going on?
network: Mask RCNN
Keras version: 2.2.4
Tensorflow version: 1.12.0
CUDA Version 9.0.176
cudnn 7.0.5
machine-learning deep-learning tensorflow cnn gpu
asked 9 hours ago
BadumBadum
487
$endgroup$
I have 2 computers:
First with GTX1050:
Epoch 1/1
200/200 [==============================] - 490s 2s/step - loss: 1.8045 - rpn_class_loss: 0.0629 - rpn_bbox_loss: 0.4044 - mrcnn_class_loss: 0.3132 - mrcnn_bbox_loss: 0.5639 - mrcnn_mask_loss: 0.4601 - val_loss: 2.6684 - val_rpn_class_loss: 0.0712 - val_rpn_bbox_loss: 1.0801 - val_mrcnn_class_loss: 0.3276 - val_mrcnn_bbox_loss: 0.6830 - val_mrcnn_mask_loss: 0.5066
CPU times: user 12min 22s, sys: 29.9 s, total: 12min 51s
Wall time: 8min 40s
Second with GTX TITAN X:
Epoch 1/1
200/200 [==============================] - 461s 2s/step - loss: 1.7415 - rpn_class_loss: 0.0592 - rpn_bbox_loss: 0.4563 - mrcnn_class_loss: 0.2490 - mrcnn_bbox_loss: 0.5253 - mrcnn_mask_loss: 0.4517 - val_loss: 1.9419 - val_rpn_class_loss: 0.0657 - val_rpn_bbox_loss: 0.6273 - val_mrcnn_class_loss: 0.2827 - val_mrcnn_bbox_loss: 0.5468 - val_mrcnn_mask_loss: 0.4194
CPU times: user 4min 34s, sys: 7.73 s, total: 4min 42s
Wall time: 10min 32s
What is it CPU times? I use tensorflow-gpu... Should be GPU-times?
What is going on?
network: Mask RCNN
Keras version: 2.2.4
Tensorflow version: 1.12.0
CUDA Version 9.0.176
cudnn 7.0.5
machine-learning deep-learning tensorflow cnn gpu
machine-learning deep-learning tensorflow cnn gpu
asked 9 hours ago
BadumBadum
487
asked 9 hours ago
BadumBadum
487
asked 9 hours ago
BadumBadum
487
asked 9 hours ago
BadumBadum
487
asked 9 hours ago
BadumBadum
487
487
put on hold as unclear what you're asking by D.W., Dawny33♦ 7 hours ago
Please clarify your specific problem or add additional details to highlight exactly what you need. As it's currently written, it’s hard to tell exactly what you're asking. See the How to Ask page for help clarifying this question. If this question can be reworded to fit the rules in the help center, please edit the question.
put on hold as unclear what you're asking by D.W., Dawny33♦ 7 hours ago
Please clarify your specific problem or add additional details to highlight exactly what you need. As it's currently written, it’s hard to tell exactly what you're asking. See the How to Ask page for help clarifying this question. If this question can be reworded to fit the rules in the help center, please edit the question.
add a comment |
add a comment |
0
active
oldest
votes
0
active
oldest
votes
0
active
oldest
votes
active
oldest
votes
active
oldest
votes
