Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

error: trained model does not exist: /tmp/mozilla_by17061430/sparse-to-dense-master/results/nyudepthv2.input=rgbd.nsample=100.rep=linear.encoder=conv.decoder=upproj.criterion=l1.lr=0.01.bs=16.pretrained=true/model_best.t7 #20

Open
wuheng199112068 opened this issue Mar 15, 2019 · 0 comments

Comments

@wuheng199112068
Copy link

error: trained model does not exist: /tmp/mozilla_by17061430/sparse-to-dense-master/results/nyudepthv2.input=rgbd.nsample=100.rep=linear.encoder=conv.decoder=upproj.criterion=l1.lr=0.01.bs=16.pretrained=true/model_best.t7
Usage: [options]

Sparse-to-Dense Training script
See https:/fangchangma/sparse-to-dense for details

Train Options:
-dataset Options: nyudepthv2 | kitti [nyudepthv2]
-inputType Options: rgb | rgbd | d | g | gd [rgb]
-nSample average number of depth samples [0]
-criterion Options: l1 | l2 | berhu [l1]
-pretrain use pretrained model [false]
-rep Representation of depth. Options: linear | log | inverse [linear]
-encoderType Options: conv | channeldrop | depthsep [conv]
-decoderType Options: deconv2 | deconv3 | upconv | upproj [upproj]
-manualSeed Manually set RNG seed [0]
-nGPU Number of GPUs to use by default [1]
-backend Options: cudnn | cunn [cudnn]
-cudnn Options: fastest | default | deterministic [fastest]
-gen Path to save generated files [gen]
-precision Options: single | double | half [single]
-nThreads number of data loading threads [2]
-nEpochs Number of total epochs to run [20]
-epochNumber Manual epoch number (useful on restarts) [1]
-batchSize mini-batch size (1 = pure stochastic) [16]
-testOnly Run on validation set only [false]
-tenCrop Ten-crop testing [false]
-resume Path to directory containing checkpoint [none]
-LR initial learning rate [0.01]
-momentum momentum [0.9]
-weightDecay weight decay [0.0001]
-recomputeBatchNorm recompute batch norm statistics [false]
-shortcutType Options: A | B | C []
-optimState Path to an optimState to reload from [none]
-optnet Use optnet to reduce memory usage [true]
-nClasses Number of classes in the dataset [0]

非常感谢你提供的代码,我对lua语言不熟,在运行命令行的时候出了以上的错误,这是为什么?你能够提供一个直接可以运行的实例吗?谢谢,盼复。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant