-
Notifications
You must be signed in to change notification settings - Fork 76
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Got very low recall when running script_rpn_bf_pedestrian_VGG16_caltech_demo #17
Comments
Hi, The model is trained on the caltech dataset. And its properties might be different from your data. e.g. the pedestrian in caltech are in small scale and often unclear. The results might be improved after training a model on your own data. |
Hi, Might help when incearsing the number of proposals via changing the opts.nms_overlap_thres and opts.after_nms_topN. |
Then meet another error. Preparing training data...total (2) = nonempty (2) + empty (0) Error in proposal_train_caltech>generate_random_minibatch (line 195) Thanks very much! @zhangliliang |
@gy1874 You might check the data preparing part. It seems that the code only detect two image in the imdb. |
I changed the opts.nms_overlap_thres to 0.3 and the opts.after_nms_topN to 300, but the number of output proposals did not increase a lot. Maybe I should train the model use my dataset. |
Actually the nms_overlap_thres should be increase to 0.9 or 1 for retaining the proposals. Multiple stage training is used for mining the hard negatives step by step, which is helpful for the robustness of the classifier in the final stage. This technique is widely used and also called as bootstrapping. |
I followed the instruction in "Testing Demo" to see the detection results on my own dataset, but I got very low recall disagree with the results in the paper. Did I get something wrong? Thanks a lot.
![roc_test167_](https://cloud.githubusercontent.com/assets/21055757/19996202/e4811868-a298-11e6-8719-217a73bd7d65.png)
Here is the ROC I got:
The text was updated successfully, but these errors were encountered: