-
Notifications
You must be signed in to change notification settings - Fork 255
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
where is the pretrained model ''models/peleenetv2_inet_288_7243.caffemodel" in train_voc.py line 242? #11
Comments
Hi,@Robert-JunWang where i can find the pretrained model? In your paper "first train on COCO trainval135k then fine-tune on 07+12",but in the train_coco.py ,you also use the pretrained model . Thank you ! |
@zhaihongjia |
@foralliance Thank you! Why use this model with two different names? |
You can use --weights to set the pre-trained model. By default, Pelee uses the model trained on ImageNet to initialize the weights. To fine-tune COCO model on VOC, you have to extract a VOC model from a pre-trained COCO model first. The detail information can be found on SSD |
I copy this model models/peleenet_inet_acc7243.caffemodel and rename it to models/peleenetv2_inet_288_7243.caffemodel. |
hello,how do you solve it. |
I miss the same problem now ! Can you give me a useful peleenetv2_inet_288_7243.caffemodel. |
hello ,solve it ?can you tell me how to solve it ? |
No description provided.
The text was updated successfully, but these errors were encountered: