MXnet 微调保存模型
MXnet fine-tune save model
我正在使用 mxnet 的微调示例通过以下代码微调我自己的数据:
https://github.com/dmlc/mxnet/blob/master/example/image-classification/fine-tune.py
看了common/fit.py,不知道微调的时候怎么保存临时模型
例如,我想每5000次迭代保存一次.params文件,我该怎么做?
谢谢!
http://mxnet.io/api/python/callback.html
尝试使用 mx.callback API.
module.fit(iterator, num_epoch=n_epoch,
... epoch_end_callback = mx.callback.do_checkpoint("mymodel", 1))
Start training with [cpu(0)]
Epoch[0] Resetting Data Iterator
Epoch[0] Time cost=0.100
Saved checkpoint to "mymodel-0001.params"
Epoch[1] Resetting Data Iterator
Epoch[1] Time cost=0.060
Saved checkpoint to "mymodel-0002.params"
我正在使用 mxnet 的微调示例通过以下代码微调我自己的数据:
https://github.com/dmlc/mxnet/blob/master/example/image-classification/fine-tune.py
看了common/fit.py,不知道微调的时候怎么保存临时模型
例如,我想每5000次迭代保存一次.params文件,我该怎么做? 谢谢!
http://mxnet.io/api/python/callback.html
尝试使用 mx.callback API.
module.fit(iterator, num_epoch=n_epoch,
... epoch_end_callback = mx.callback.do_checkpoint("mymodel", 1))
Start training with [cpu(0)]
Epoch[0] Resetting Data Iterator
Epoch[0] Time cost=0.100
Saved checkpoint to "mymodel-0001.params"
Epoch[1] Resetting Data Iterator
Epoch[1] Time cost=0.060
Saved checkpoint to "mymodel-0002.params"