fix fine-tuning example: paths, test acc., and total fine-tuning time

1 files changed, 33 insertions, 32 deletions

diff --git a/examples/finetune_flickr_style/readme.md b/examples/finetune_flickr_style/readme.md
index dad45aeb..4220102e 100644
--- a/examples/finetune_flickr_style/readme.md
+++ b/examples/finetune_flickr_style/readme.md
@@ -60,7 +60,7 @@ We'll also need the ImageNet-trained model, which you can obtain by running `./s
 
 Now we can train! (You can fine-tune in CPU mode by leaving out the `-gpu` flag.)
 
-    caffe % ./build/tools/caffe train -solver models/finetune_flickr_style/flickr_style_solver.prototxt -weights models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel -gpu 0
+    caffe % ./build/tools/caffe train -solver models/finetune_flickr_style/solver.prototxt -weights models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel -gpu 0
 
     [...]
 
@@ -72,77 +72,78 @@ Now we can train! (You can fine-tune in CPU mode by leaving out the `-gpu` flag.
 
     I0828 22:17:48.338963 11510 solver.cpp:165] Solving FlickrStyleCaffeNet
     I0828 22:17:48.339010 11510 solver.cpp:251] Iteration 0, Testing net (#0)
-    I0828 22:18:14.313817 11510 solver.cpp:302]     Test net output #0: accuracy = 0.0416
-    I0828 22:18:14.476822 11510 solver.cpp:195] Iteration 0, loss = 3.75717
+    I0828 22:18:14.313817 11510 solver.cpp:302]     Test net output #0: accuracy = 0.0308
+    I0828 22:18:14.476822 11510 solver.cpp:195] Iteration 0, loss = 3.78589
     I0828 22:18:14.476878 11510 solver.cpp:397] Iteration 0, lr = 0.001
-    I0828 22:18:19.700408 11510 solver.cpp:195] Iteration 20, loss = 3.1689
+    I0828 22:18:19.700408 11510 solver.cpp:195] Iteration 20, loss = 3.25728
     I0828 22:18:19.700461 11510 solver.cpp:397] Iteration 20, lr = 0.001
-    I0828 22:18:24.924685 11510 solver.cpp:195] Iteration 40, loss = 2.3549
+    I0828 22:18:24.924685 11510 solver.cpp:195] Iteration 40, loss = 2.18531
     I0828 22:18:24.924741 11510 solver.cpp:397] Iteration 40, lr = 0.001
-    I0828 22:18:30.114858 11510 solver.cpp:195] Iteration 60, loss = 2.74191
+    I0828 22:18:30.114858 11510 solver.cpp:195] Iteration 60, loss = 2.4915
     I0828 22:18:30.114910 11510 solver.cpp:397] Iteration 60, lr = 0.001
-    I0828 22:18:35.328071 11510 solver.cpp:195] Iteration 80, loss = 1.9147
+    I0828 22:18:35.328071 11510 solver.cpp:195] Iteration 80, loss = 2.04539
     I0828 22:18:35.328127 11510 solver.cpp:397] Iteration 80, lr = 0.001
-    I0828 22:18:40.588317 11510 solver.cpp:195] Iteration 100, loss = 1.81419
+    I0828 22:18:40.588317 11510 solver.cpp:195] Iteration 100, loss = 2.1924
     I0828 22:18:40.588373 11510 solver.cpp:397] Iteration 100, lr = 0.001
-    I0828 22:18:46.171576 11510 solver.cpp:195] Iteration 120, loss = 2.02105
+    I0828 22:18:46.171576 11510 solver.cpp:195] Iteration 120, loss = 2.25107
     I0828 22:18:46.171669 11510 solver.cpp:397] Iteration 120, lr = 0.001
-    I0828 22:18:51.757809 11510 solver.cpp:195] Iteration 140, loss = 1.49083
+    I0828 22:18:51.757809 11510 solver.cpp:195] Iteration 140, loss = 1.355
     I0828 22:18:51.757863 11510 solver.cpp:397] Iteration 140, lr = 0.001
-    I0828 22:18:57.345080 11510 solver.cpp:195] Iteration 160, loss = 1.35319
+    I0828 22:18:57.345080 11510 solver.cpp:195] Iteration 160, loss = 1.40815
     I0828 22:18:57.345135 11510 solver.cpp:397] Iteration 160, lr = 0.001
-    I0828 22:19:02.928794 11510 solver.cpp:195] Iteration 180, loss = 1.11658
+    I0828 22:19:02.928794 11510 solver.cpp:195] Iteration 180, loss = 1.6558
     I0828 22:19:02.928850 11510 solver.cpp:397] Iteration 180, lr = 0.001
-    I0828 22:19:08.514497 11510 solver.cpp:195] Iteration 200, loss = 1.08851
+    I0828 22:19:08.514497 11510 solver.cpp:195] Iteration 200, loss = 0.88126
     I0828 22:19:08.514552 11510 solver.cpp:397] Iteration 200, lr = 0.001
 
     [...]
 
-    I0828 22:22:40.789010 11510 solver.cpp:195] Iteration 960, loss = 0.0844627
+    I0828 22:22:40.789010 11510 solver.cpp:195] Iteration 960, loss = 0.112586
     I0828 22:22:40.789175 11510 solver.cpp:397] Iteration 960, lr = 0.001
-    I0828 22:22:46.376626 11510 solver.cpp:195] Iteration 980, loss = 0.0110937
+    I0828 22:22:46.376626 11510 solver.cpp:195] Iteration 980, loss = 0.0959077
     I0828 22:22:46.376682 11510 solver.cpp:397] Iteration 980, lr = 0.001
     I0828 22:22:51.687258 11510 solver.cpp:251] Iteration 1000, Testing net (#0)
-    I0828 22:23:17.438894 11510 solver.cpp:302]     Test net output #0: accuracy = 1
+    I0828 22:23:17.438894 11510 solver.cpp:302]     Test net output #0: accuracy = 0.2356
 
-Note how rapidly the loss went down. Although the 100% accuracy is optimistic, it is evidence the model is learning quickly and well.
+Note how rapidly the loss went down. Although the 23.5% accuracy is only modest, it was achieved in only 1000, and evidence that the model is starting to learn quickly and well.
+Once the model is fully fine-tuned on the whole training set over 100,000 iterations the final validation accuracy is 91.64%. This takes ~7 hours in Caffe on a K40 GPU.
 
 For comparison, here is how the loss goes down when we do not start with a pre-trained model:
 
     I0828 22:24:18.624004 12919 solver.cpp:165] Solving FlickrStyleCaffeNet
     I0828 22:24:18.624099 12919 solver.cpp:251] Iteration 0, Testing net (#0)
-    I0828 22:24:44.520992 12919 solver.cpp:302]     Test net output #0: accuracy = 0.045
-    I0828 22:24:44.676905 12919 solver.cpp:195] Iteration 0, loss = 3.33111
+    I0828 22:24:44.520992 12919 solver.cpp:302]     Test net output #0: accuracy = 0.0366
+    I0828 22:24:44.676905 12919 solver.cpp:195] Iteration 0, loss = 3.47942
     I0828 22:24:44.677120 12919 solver.cpp:397] Iteration 0, lr = 0.001
-    I0828 22:24:50.152454 12919 solver.cpp:195] Iteration 20, loss = 2.98133
+    I0828 22:24:50.152454 12919 solver.cpp:195] Iteration 20, loss = 2.99694
     I0828 22:24:50.152509 12919 solver.cpp:397] Iteration 20, lr = 0.001
-    I0828 22:24:55.736256 12919 solver.cpp:195] Iteration 40, loss = 3.02124
+    I0828 22:24:55.736256 12919 solver.cpp:195] Iteration 40, loss = 3.0498
     I0828 22:24:55.736311 12919 solver.cpp:397] Iteration 40, lr = 0.001
-    I0828 22:25:01.316514 12919 solver.cpp:195] Iteration 60, loss = 2.99509
+    I0828 22:25:01.316514 12919 solver.cpp:195] Iteration 60, loss = 2.99549
     I0828 22:25:01.316567 12919 solver.cpp:397] Iteration 60, lr = 0.001
-    I0828 22:25:06.899554 12919 solver.cpp:195] Iteration 80, loss = 2.9928
+    I0828 22:25:06.899554 12919 solver.cpp:195] Iteration 80, loss = 3.00573
     I0828 22:25:06.899610 12919 solver.cpp:397] Iteration 80, lr = 0.001
-    I0828 22:25:12.484624 12919 solver.cpp:195] Iteration 100, loss = 2.99072
+    I0828 22:25:12.484624 12919 solver.cpp:195] Iteration 100, loss = 2.99094
     I0828 22:25:12.484678 12919 solver.cpp:397] Iteration 100, lr = 0.001
-    I0828 22:25:18.069056 12919 solver.cpp:195] Iteration 120, loss = 3.01816
+    I0828 22:25:18.069056 12919 solver.cpp:195] Iteration 120, loss = 3.01616
     I0828 22:25:18.069149 12919 solver.cpp:397] Iteration 120, lr = 0.001
-    I0828 22:25:23.650928 12919 solver.cpp:195] Iteration 140, loss = 2.9694
+    I0828 22:25:23.650928 12919 solver.cpp:195] Iteration 140, loss = 2.98786
     I0828 22:25:23.650984 12919 solver.cpp:397] Iteration 140, lr = 0.001
-    I0828 22:25:29.235535 12919 solver.cpp:195] Iteration 160, loss = 3.00383
+    I0828 22:25:29.235535 12919 solver.cpp:195] Iteration 160, loss = 3.00724
     I0828 22:25:29.235589 12919 solver.cpp:397] Iteration 160, lr = 0.001
-    I0828 22:25:34.816898 12919 solver.cpp:195] Iteration 180, loss = 2.99802
+    I0828 22:25:34.816898 12919 solver.cpp:195] Iteration 180, loss = 3.00099
     I0828 22:25:34.816953 12919 solver.cpp:397] Iteration 180, lr = 0.001
-    I0828 22:25:40.396656 12919 solver.cpp:195] Iteration 200, loss = 2.99769
+    I0828 22:25:40.396656 12919 solver.cpp:195] Iteration 200, loss = 2.99848
     I0828 22:25:40.396711 12919 solver.cpp:397] Iteration 200, lr = 0.001
 
     [...]
 
-    I0828 22:29:12.539094 12919 solver.cpp:195] Iteration 960, loss = 2.99314
+    I0828 22:29:12.539094 12919 solver.cpp:195] Iteration 960, loss = 2.99203
     I0828 22:29:12.539258 12919 solver.cpp:397] Iteration 960, lr = 0.001
-    I0828 22:29:18.123092 12919 solver.cpp:195] Iteration 980, loss = 2.99503
+    I0828 22:29:18.123092 12919 solver.cpp:195] Iteration 980, loss = 2.99345
     I0828 22:29:18.123147 12919 solver.cpp:397] Iteration 980, lr = 0.001
     I0828 22:29:23.432059 12919 solver.cpp:251] Iteration 1000, Testing net (#0)
-    I0828 22:29:49.409044 12919 solver.cpp:302]     Test net output #0: accuracy = 0.0624
+    I0828 22:29:49.409044 12919 solver.cpp:302]     Test net output #0: accuracy = 0.0572
 
 This model is only beginning to learn.