search

xiaolonw / adversarial-frcnn

A-Fast-RCNN (CVPR 2017)
Other
482 stars 168 forks source link

How to train this net using my own dataset? #21

Open Kongsea opened 6 years ago

Kongsea commented 6 years ago

I want to train this net using my own dataset.

I have successfully set the data, however, the number of class need to be modified and some model layers cannot be restored accordingly.

For example, when I run the code, it raised the following error:

Cannot copy param 0 weights from layer 'cls_score_readonly'; shape mismatch. Source param shape is 21 4096 (86016); target param shape is 146 4096 (598016). To learn this layer's parameters from scratch rather than copying from a saved net, rename the layer.

Cannot copy param 0 weights from layer 'cls_score'; shape mismatch. Source param shape is 21 4096 (86016); target param shape is 146 4096 (598016). To learn this layer's parameters from scratch rather than copying from a saved net, rename the layer.

So could anybody give me some advice on how to fix it? Thank you!

Kongsea commented 6 years ago

Besides, where can I download the pretrained VGG16.V2.caffemodel?

unable to open file: name = 'data/imagenet_models/VGG16.v2.caffemodel', errno = 2, error message = 'No such file or directory'

We can download it from here.