vato007/fast-depth-tf
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
13 Commits 2 Branches 0 Tags
f3fc0f8fbb6d631a75666355c879c84d1308acbf
Commit Graph

9 Commits

Author SHA1 Message Date
Piv
870429c3ef Refactor fast-depth 
Addresses the following:
 - Rename nnconv5 block to nnconv5
 - Add skip connections directly to nnconv5 block
 - Allow custom metrics, loss and optimizer (keep defaults that reflect original paper) to train
 - Correctly use nyu evaluation dataset only when no dataset is provided
 2021-03-29 17:57:12 +10:30
Piv
3325ea0c0c Format pep8, include pass shaped to mobilenet 2021-03-25 21:56:50 +10:30
Piv
78d5aace15 Remove Experimental model 
It didn't perform any better than the regular model
Removing batch normalisation significantly harmed training performance
 2021-03-25 21:28:07 +10:30
Piv
ab7da5acd4 Add documentation and README, use Upsampling2D rather than image Resizing layer 2021-03-24 21:35:25 +10:30
Piv
ac3ab27ddd Add model with no batch normalisation, use actual mobilnet model rather than extracting layers 
Found from DenseDepth, each layer can be set to trainable in the encoder, then the outputs of the
model and the required layers for skip connections can be used directly. Ends up being much cleaner
 2021-03-24 20:00:26 +10:30
Piv
39074f22a7 Add working train and eval functions for nyu_v2 2021-03-21 09:51:45 +10:30
Piv
fea08521bb Add metrics, prepare for training 2021-03-17 21:15:06 +10:30
Piv
00762f3e86 Build Functional Model, remove subclassed model 
Functional models are way easier to work with,
and I don't need any advanced features that would
require model subclassing
 2021-03-17 18:24:46 +10:30
Piv
b25b9be4eb Initial Commit 2021-03-16 21:06:27 +10:30