Open CeciliaYao opened 1 year ago
Or is it because the checkpoint of mpvit_base,pth
is currently provided? Would you release this ckpt model to us for learning and training? Thank you so much!
hello, classmate, could you please send me a copy of the complete code? I have been studying this paper recently, and my email is 1131806140@qq.com
thank you !!!!!!
So do you test the suggested network ?(mpvit_small)
For the mpvit_base part, you can only define an attention layer like:
self.convs["f0"] = Attention_Module(self.ch_enc[0] , num_ch_enc[0])
and process the feature[0] as:
feat[0] = self.convs["f0"](input_features[0])
Do not need to change the param. of num_ch_enc;
thank you !!!!!!
Could you send me the code? I'm having problems adjusting the train.py and trainer.py files. my mail is: amin.ayechi.2001@gmail.com
Dear author,
Thank you for your fantastic contribution ! However,I had some problems reproducing the results of
MPViT-base
. I'd really appreciate it if you would help me check what the problem is :-) @zxcqlfI eval my MPViT-base model on KITTI and got the following results:
I think it may be because I set
num_ch_enc
orch_enc
incorrectly in depth_decoder, would you help me confirm what the correct value should be?hr_decoder.py
by changingself.num_ch_dec
tonp.array([64, 64, 128, 256, 512])
as shown below.Secondly, in
trainer.py
, I reassigned thech_enc
andnum_ch_enc
arguments to DepthDecoder. It looks like this:Finally, in
evaluate_depth.py
, I changed the parameters of the encoder and decoder.As a supplement, my training loss looks like this:
Thank you for your time and assistance!