caffe 损失为 nan 或 0
caffe loss is nan or 0
我正在训练一个网络，我已经将学习率从 0.1 更改为 0.00001。输出始终保持不变。没有平均值用于训练。
造成如此奇怪损失的原因可能是什么？
I1107 15:07:28.381621 12333 solver.cpp:404] Test net output #0: loss = 3.37134e+11 (* 1 = 3.37134e+11 loss)
I1107 15:07:28.549142 12333 solver.cpp:228] Iteration 0, loss = 1.28092e+11
I1107 15:07:28.549201 12333 solver.cpp:244] Train net output #0: loss = 1.28092e+11 (* 1 = 1.28092e+11 loss)
I1107 15:07:28.549211 12333 sgd_solver.cpp:106] Iteration 0, lr = 1e-07
I1107 15:07:59.490077 12333 solver.cpp:228] Iteration 50, loss = -nan
I1107 15:07:59.490170 12333 solver.cpp:244] Train net output #0: loss = 0 (* 1 = 0 loss)
I1107 15:07:59.490176 12333 sgd_solver.cpp:106] Iteration 50, lr = 1e-07
I1107 15:08:29.177093 12333 solver.cpp:228] Iteration 100, loss = -nan
I1107 15:08:29.177119 12333 solver.cpp:244] Train net output #0: loss = 0 (* 1 = 0 loss)
I1107 15:08:29.177125 12333 sgd_solver.cpp:106] Iteration 100, lr = 1e-07
I1107 15:08:59.758381 12333 solver.cpp:228] Iteration 150, loss = -nan
I1107 15:08:59.758513 12333 solver.cpp:244] Train net output #0: loss = 0 (* 1 = 0 loss)
I1107 15:08:59.758545 12333 sgd_solver.cpp:106] Iteration 150, lr = 1e-07
I1107 15:09:30.210208 12333 solver.cpp:228] Iteration 200, loss = -nan
I1107 15:09:30.210304 12333 solver.cpp:244] Train net output #0: loss = 0 (* 1 = 0 loss)
I1107 15:09:30.210310 12333 sgd_solver.cpp:106] Iteration 200, lr = 1e-07
你的损失不是0，甚至没有接近。您从 3.3e+11（即 ~10^11）开始，似乎在它爆炸后不久您会得到 nan。您需要大幅降低损失值。如果您使用 "EuclideanLoss"，您可能希望通过深度图的大小来平均损失，将预测值缩放到 [-1,1] 范围，或任何其他可以防止损失爆炸的缩放方法。
我正在训练一个网络，我已经将学习率从 0.1 更改为 0.00001。输出始终保持不变。没有平均值用于训练。 造成如此奇怪损失的原因可能是什么？
I1107 15:07:28.381621 12333 solver.cpp:404] Test net output #0: loss = 3.37134e+11 (* 1 = 3.37134e+11 loss)
I1107 15:07:28.549142 12333 solver.cpp:228] Iteration 0, loss = 1.28092e+11
I1107 15:07:28.549201 12333 solver.cpp:244] Train net output #0: loss = 1.28092e+11 (* 1 = 1.28092e+11 loss)
I1107 15:07:28.549211 12333 sgd_solver.cpp:106] Iteration 0, lr = 1e-07
I1107 15:07:59.490077 12333 solver.cpp:228] Iteration 50, loss = -nan
I1107 15:07:59.490170 12333 solver.cpp:244] Train net output #0: loss = 0 (* 1 = 0 loss)
I1107 15:07:59.490176 12333 sgd_solver.cpp:106] Iteration 50, lr = 1e-07
I1107 15:08:29.177093 12333 solver.cpp:228] Iteration 100, loss = -nan
I1107 15:08:29.177119 12333 solver.cpp:244] Train net output #0: loss = 0 (* 1 = 0 loss)
I1107 15:08:29.177125 12333 sgd_solver.cpp:106] Iteration 100, lr = 1e-07
I1107 15:08:59.758381 12333 solver.cpp:228] Iteration 150, loss = -nan
I1107 15:08:59.758513 12333 solver.cpp:244] Train net output #0: loss = 0 (* 1 = 0 loss)
I1107 15:08:59.758545 12333 sgd_solver.cpp:106] Iteration 150, lr = 1e-07
I1107 15:09:30.210208 12333 solver.cpp:228] Iteration 200, loss = -nan
I1107 15:09:30.210304 12333 solver.cpp:244] Train net output #0: loss = 0 (* 1 = 0 loss)
I1107 15:09:30.210310 12333 sgd_solver.cpp:106] Iteration 200, lr = 1e-07
你的损失不是0，甚至没有接近。您从 3.3e+11（即 ~10^11）开始，似乎在它爆炸后不久您会得到 nan。您需要大幅降低损失值。如果您使用 "EuclideanLoss"，您可能希望通过深度图的大小来平均损失，将预测值缩放到 [-1,1] 范围，或任何其他可以防止损失爆炸的缩放方法。