You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi k3nt0w,
I use your FCN to do semantic image segmentation.
After I train FCN and run predict.py (visualize(predict("2011_003151", "FCN"), "2011_003151")), the result image is always blank.
I have no idea about this result.
Could you have any suggestion?
Hi k3nt0w,
I use your FCN to do semantic image segmentation.
After I train FCN and run predict.py (visualize(predict("2011_003151", "FCN"), "2011_003151")), the result image is always blank.
I have no idea about this result.
Could you have any suggestion?
There is my training result:
python train.py
Using Theano backend.
Epoch 1/20
20/20 [==============================] - 47s - loss: 3.0276 - acc: 0.4169
Epoch 2/20
20/20 [==============================] - 45s - loss: 1.8475 - acc: 0.7483
Epoch 3/20
20/20 [==============================] - 61s - loss: 2.1842 - acc: 0.6822
Epoch 4/20
20/20 [==============================] - 55s - loss: 1.6089 - acc: 0.7439
Epoch 5/20
20/20 [==============================] - 50s - loss: 1.4220 - acc: 0.7532
Epoch 6/20
20/20 [==============================] - 46s - loss: 1.8194 - acc: 0.6313
Epoch 7/20
20/20 [==============================] - 45s - loss: 1.2417 - acc: 0.7648
Epoch 8/20
20/20 [==============================] - 46s - loss: 1.2862 - acc: 0.7911
Epoch 9/20
20/20 [==============================] - 45s - loss: 1.4306 - acc: 0.7102
Epoch 10/20
20/20 [==============================] - 45s - loss: 1.1640 - acc: 0.8106
Epoch 11/20
20/20 [==============================] - 45s - loss: 1.7805 - acc: 0.6463
Epoch 12/20
20/20 [==============================] - 46s - loss: 1.4626 - acc: 0.7167
Epoch 13/20
20/20 [==============================] - 45s - loss: 0.9658 - acc: 0.8034
Epoch 14/20
20/20 [==============================] - 45s - loss: 1.4806 - acc: 0.7155
Epoch 15/20
20/20 [==============================] - 46s - loss: 1.1805 - acc: 0.8013
Epoch 16/20
20/20 [==============================] - 46s - loss: 1.3589 - acc: 0.7372
Epoch 17/20
20/20 [==============================] - 51s - loss: 1.3243 - acc: 0.7290
Epoch 18/20
20/20 [==============================] - 52s - loss: 1.1608 - acc: 0.7704
Epoch 19/20
20/20 [==============================] - 51s - loss: 1.2211 - acc: 0.7372
Epoch 20/20
20/20 [==============================] - 47s - loss: 0.8725 - acc: 0.7926
Regards,
chungfu27
The text was updated successfully, but these errors were encountered: