search

Seanlinx / mtcnn

595 stars 264 forks source link

How to save the trained model #22

Open peyer opened 7 years ago

peyer commented 7 years ago

If I want to save the pnet/rnet/onet model , should I add mod.save(...) after mod.fit(...) in train.py?

Seanlinx commented 7 years ago

No, it's done in epoch end callback inside mod.fit()

peyer commented 7 years ago

thanks a lot

peyer commented 7 years ago

I'm sorry , but when I train the pnet again using your gen_pnet_data.py and lr = 0.01 , the output become nan again . I feel so bad .

zhanglaplace commented 7 years ago

@peyer can you share me the blog about how to train the Mtcnn.

anna0709 commented 6 years ago

@peyer Hi, I am new in mxnet, and I want to retrain P and R and net on the dataset of wider face. I had run transform.py to get anno.txt, then run gen_pnet_data.py and gen_hard_example.py, what should I do next? run train_P_net.py ? could you please tell me the whole step of training?