torch/nn

Issues

• BatchNormalization.lua:87: got 32-feature tensor, expected 0

  #1327 opened 2 years ago by emredog
  1

• same sentence different padding length result different embedding because softmax precision

  #1326 opened 3 years ago by JJplane
  0

• How to resume training from a certain epoch or how to update an already trained model in torch ?

  #1305 opened 6 years ago by maryam089
  1

• Compatibility issues

  #1324 opened 4 years ago by kysunami
  0

• install/share/lua/5.1/nn/LookupTable.lua:73: bad argument #3 to 'index' (Tensor | LongTensor expected, got torch.CudaLongTensor)

  #1323 opened 5 years ago by m0dulo
  0

• SpatialDepthWiseConvolution swaps height and width

  #1307 opened 6 years ago by diovisgood
  3

• Backprop procedure for nn.Narrow

  #1322 opened 6 years ago by pskrunner14
  0

• Cannot run Torch train command – NYI stack traceback

  #1321 opened 6 years ago by matthewclark4
  0

• getParamsByDevice Branch problem

  #1293 opened 7 years ago by MikeChenfu
  1

• TripletCriterion (aka triplet loss) missing

  #1320 opened 6 years ago by jatinsha
  0

• parallelcriterion has no length operator

  #1317 opened 6 years ago by 980380446
  0

• Ask a question of nn.SplitTable？

  #1312 opened 6 years ago by xtanitfy
  1

• Does the nn library use Tensor Core on Nvidia V100 GPU?

  #1294 opened 7 years ago by michaelhuang74
  1

• FastLSTM out of memory error

  #1316 opened 6 years ago by tastyminerals
  0

• Why gradInput of nn.Mul is computed by gradOutput add by weight rather than multiply by weight?

  #1315 opened 6 years ago by ChunyanZhao
  0

• ClassNLLCriterion.cu t < n_classes failed.

  #1314 opened 6 years ago by skynbe
  0

• Simple real time object detection using Torch

  #1313 opened 6 years ago by VictorQueiroz
  0

• nn.test() fails: Kmeans - invalid arguments (CudaLongTensor)

  #1311 opened 6 years ago by abachaa
  0

• UpSample

  #1310 opened 6 years ago by tongqcx
  0

• Using nn.Padding throws luajit: C++ exception

  #1309 opened 6 years ago by tastyminerals
  0

• Strange behavior of nn.Padding during training

  #1308 opened 6 years ago by tastyminerals
  0

• Simple neural net has different output for inputs in the same batch that are identical

  #1306 opened 6 years ago by happypepper
  11

• The getParameters() function cannot work with the module designed in the criterion part of document

  #1304 opened 6 years ago by hfxunlp
  4

• ParallelCriterion input form?

  #1302 opened 6 years ago by jmfu95
  4

• /torch/install/share/lua/5.1/nn/LookupTable.lua:59: attempt to call method 'Contiguous' (a nil value)

  #1301 opened 6 years ago by jmfu95
  0

• **Facing dimension problem, when I include Dropout into the network**

  #1300 opened 6 years ago by badripatro
  0

• Bad Argument

  #1299 opened 6 years ago by zaktab
  4

• Uses the deprecated package ffi

  #1298 opened 7 years ago by yurivict
  1

• Issue with type conversion for BatchNorm inference in THNN

  #1296 opened 7 years ago by libfun
  1

• How to separate a network into submodules

  #1295 opened 7 years ago by SeunghyunMoon
  0

• nn.FeatureLPPooling has been already assigned a parent class

  #1292 opened 7 years ago by MikeChenfu
  2

• MSECriterion_updateGradInput error: cannot convert 'struct THCudaHalfTensor *' to 'struct THCudaTensor *

  #1290 opened 7 years ago by michaelhuang74
  0

• nn.Recurrent() function is missing!

  #1289 opened 7 years ago by Elyorcv
  1

• Inconsistence in SpatialMaxPooling and SpatialMaxUnpooling operations for torch.CudaTensor that leads to an error

  #1287 opened 7 years ago by borismu
  0

• How to use nn.ParallelTable() inside nn.Sequential()

  #1286 opened 7 years ago by mbcel
  1

• Why isn't the error scaled down during Mul's backprop ?

  #1285 opened 7 years ago by singam-sanjay
  0

• Is there a module that does bilinear interpolation on sparse inputs?

  #1281 opened 7 years ago by mbcel
  0

• Bug: Inconsistence of the channel of `input` and that of `self.gradInput` can also work!

  #1279 opened 7 years ago by Naruto-Sasuke
  0

• multi target not supported issue in ClassNLLCriterion

  #1278 opened 7 years ago by dephaniehe
  0

• which lua file can implement SpatialGridSamplerBilinear.c function?

  #1265 opened 7 years ago by csxmli2016
  4

• Problem with backpropagation when combining Reshape() and Padding()

  #1276 opened 7 years ago by tlemberger
  0

• SpatialSubtractiveNormalization fails when cloning with shared weights

  #1274 opened 7 years ago by etrulls
  0

• torch.nn in context of a cuda stream

  #1273 opened 7 years ago by uriv
  3

• VolumetricConvolution + ReLU

  #1268 opened 7 years ago by ebsrn
  0

• VolumetricUpSamplingNearest module

  #1272 opened 7 years ago by mks0601
  0

• Inconsistency in nn.HardShrink() activation function?

  #1270 opened 7 years ago by NataliaDiaz
  1

• [Linear Layer] Possibly wrong gradient?

  #1269 opened 7 years ago by cdluminate
  2

• Why is not nn.MSDCriterion() listed in https://github.com/torch/nn/blob/master/doc/criterion.md ?

  #1266 opened 7 years ago by NataliaDiaz
  2

• Volumetric Upsampling Modules Release Date

  #1262 opened 7 years ago
  7

• nn.SpatialUpSamplingBilinear (a nil value)

  #1263 opened 7 years ago by abdullahjamal
  1