Closed DYJ1111 closed 4 years ago
Which one of the output channels?
You can change the channel of FPN like this.
Which one of the output channels?
You can change the channel of FPN like this.
So you mean that I can use the vovnet VoVNet19_slim_eSE = { 'stem': [64, 64, 128], 'stage_conv_ch': [64, 80, 96, 112], 'stage_out_ch': [112, 256, 384, 512], 'layer_per_block': 3, 'block_per_stage': [1, 1, 1, 1], 'eSE' : True, "dw" : False }as the conv body. when i want to classify, I just map 512 to 128?
I cannot figure out what you mean.
Please explain more details what you want.
Do you want to use vovnet for image classification task?
I cannot figure out what you mean.
Please explain more details what you want.
Do you want to use vovnet for image classification task?
I want to do a speech classification task, the embedding size of the classification is set to 128, according to the parameter settings provided in the paper, the embedding size is 512, so I think it is possible to adjust the parameters to make the embedding size generated by the network become 128
I see,
I recommend
if you want to use the pretrained weight, you don't need to change the original parameter of vovnet. Instead, you add global average pooling - fc with 128 channels.
like ResNet for classification
I see,
I recommend
if you want to use the pretrained weight, you don't need to change the original parameter of vovnet. Instead, you add global average pooling - fc with 128 channels.
like ResNet for classification
Are there any training strategies that need attention, such as learning rate and number of iterations?
@DYJ1111
The training protocols such as learning rate and schedule, etc depend on your task and GPU envrionment.
@DYJ1111
The training protocols such as learning rate and schedule, etc depend on your task and GPU envrionment.
ok, thank you
Hello, I want to change the output channel to be 128, Could you give me some advice about how to modify the params? The params I set can not get a good result. The result is worse than ResNet34.
Looking forward your reply.