search

aimerykong / predictive-filter-flow

Predictive Filter Flow for fully/self-supervised learning on various vision tasks
https://www.ics.uci.edu/~skong2/mgpff.html
140 stars 24 forks source link

Typo ? #12

Closed AlbertZhangHIT closed 4 years ago

AlbertZhangHIT commented 4 years ago

Hi, In PFF_image/libs_deblur/models/pixel_embedding_model.py, 

...
line 165         out = self.layer1(out)        
line 166         out_layer1 = self.layer1_dimRed(out)        
line 167         out_layer1 = self.interp_x4(out_layer1)
line 167         out_layer1 = self.layer2_feats(out_layer1)
...
line 366         out = self.layer1(out)        
line 367         out_layer1 = self.layer1_dimRed(out)        
line 368         out_layer1 = self.interp_x4(out_layer1)
line 369         out_layer1 = self.layer2_feats(out_layer1)
...
line 542         out = self.layer1(out)        
line 543         out_layer1 = self.layer1_dimRed(out)        
line 544         out_layer1 = self.interp_x4(out_layer1)
line 545         out_layer1 = self.layer2_feats(out_layer1)
...
line 716         out = self.layer1(out)        
line 717         out_layer1 = self.layer1_dimRed(out)        
line 718         out_layer1 = self.interp_x4(out_layer1)
line 719         out_layer1 = self.layer2_feats(out_layer1)
...

All layer1 features you used self.layer2_feats, maybe there is something wrong with this.

aimerykong commented 4 years ago

Hi, Hao, Yes! That is a bug! Thank you for checking the code. I also found this recently, yet didn't have chance to update the github:-) Hope this does not bother you too much. Regards, Shu

On Wed, Nov 27, 2019 at 2:33 PM Hao Zhang notifications@github.com wrote:

Hi, In PFF_image/libs_deblur/models/pixel_embedding_model.py,

... line 165 out = self.layer1(out) line 166 out_layer1 = self.layer1_dimRed(out) line 167 out_layer1 = self.interp_x4(out_layer1) line 167 out_layer1 = self.layer2_feats(out_layer1) ... line 366 out = self.layer1(out) line 367 out_layer1 = self.layer1_dimRed(out) line 368 out_layer1 = self.interp_x4(out_layer1) line 369 out_layer1 = self.layer2_feats(out_layer1) ... line 542 out = self.layer1(out) line 543 out_layer1 = self.layer1_dimRed(out) line 544 out_layer1 = self.interp_x4(out_layer1) line 545 out_layer1 = self.layer2_feats(out_layer1) ... line 716 out = self.layer1(out) line 717 out_layer1 = self.layer1_dimRed(out) line 718 out_layer1 = self.interp_x4(out_layer1) line 719 out_layer1 = self.layer2_feats(out_layer1) ...

All layer1 features you used self.layer2_feats, maybe there is something wrong with this.

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/aimerykong/predictive-filter-flow/issues/12?email_source=notifications&email_token=ABRJSJCYBOQUPRKHUG7YCN3QV3YS3A5CNFSM4JSM56HKYY3PNVWWK3TUL52HS4DFUVEXG43VMWVGG33NNVSW45C7NFSM4H4RCJ2A, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABRJSJHVLJEHQXJ2MI26HOLQV3YS3ANCNFSM4JSM56HA .