Last active
August 29, 2015 14:14
-
-
Save vaibhaw/a9e6ec39c4044881ddc3 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
solver.prototxt | |
1. net: | |
2. snapshot_prefix: | |
3. solver_mode: | |
Optional | |
test_interval: | |
max_iter: | |
snapshot: | |
train_val.prototxt | |
1. source: # 2 occurences | |
2. num_output: | |
3. blob_lr: # change it to zero for layers which need not be trained | |
4. image_size | |
code: ./build/tools/caffe train -solver models/finetune_flickr_style/solver.prototxt -weights models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel -gpu 0 | |
deploy.prototxt | |
1. num_output: | |
2. image_size: | |
## check number of images per combinatio of labels | |
# e.g. images with label 1 3 | |
# script written for the case when there are only 2 labels | |
# label 1 has classes from 0 to 7 and label 2 has classes from 0 to 4 | |
for i in $(seq 0 7); do for j in $(seq 0 4); do printf "%2d %2d:\t" "$i" "$j"; cat train.txt | grep " $i $j" | wc -l; done; done |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment