Feature/darknet #356
Feature/darknet #356
Conversation
junjihashimoto
commented
Apr 17, 2020
•
junjihashimoto
commented
- Parser for darknet init file
- [] Read darknet weight file
- [] Implement yolov3
junjihashimoto
force-pushed
the
feature/darknet
branch
from
c221f32
to
b232244
Compare
junjihashimoto
force-pushed
the
feature/darknet
branch
from
fb5116b
to
30687b6
Compare
hasktorch/src/Torch/NN.hs
Outdated
| @@ -48,11 +51,36 @@ instance Parameterized Parameter where | |||
| flattenParameters = pure | |||
| replaceOwnParameters _ = nextParameter | |||
|
|
|||
| instance Parameterized a => Parameterized [a] where | |||
There was a problem hiding this comment.
for this instance maybe you can also use this generalized version (sorry I hadn't gotten around to fixing the other one there yet, but this one seems good).
There was a problem hiding this comment.
Thanks for your suggestion.
I've changed the instance with generalized one.
Untyped instance can be fixed with 'OVERLAPS' pragma.
But typed instance can not be fixed with 'OVERLAPS' pragma.(I don't know why.)
hasktorch/src/Torch/NN.hs
Outdated
| instance Parameterized Double where | ||
| flattenParameters _ = [] | ||
| replaceOwnParameters = return | ||
|
|
||
| instance Parameterized [Int] where | ||
| instance Parameterized Float where |
There was a problem hiding this comment.
for this one I tried instance (Scalar a) => Parameterized a, but GHC felt that was not okay. 😕
| @@ -153,7 +178,7 @@ data Conv2d = | |||
| Conv2d { | |||
| conv2dWeight :: Parameter, | |||
| conv2dBias :: Parameter | |||
| } deriving (Show, Generic) | |||
| } deriving (Show, Generic, Parameterized) | |||
There was a problem hiding this comment.
we can do that now? that's great! :)
| let [a,b] = asValue v | ||
| in (a,b) | ||
| _dtype = error "Not implemented for tuple-type" | ||
| _dims v = error "Not implemented for tuple-type" |
| let pad = (layerSize - 1) `div` 2 | ||
| activation = if isLeaky then flip I.leaky_relu 0.1 else id | ||
| in activation | ||
| $ batchNormForward batchNorm train 0.90000000000000002 1.0000000000000001e-05 |
junjihashimoto
force-pushed
the
feature/darknet
branch
from
30687b6
to
8096c74
Compare
|
@tycho01 Thank you for your reviewing. |
| Int -> | ||
| -- | [1, 1, grid, grid] | ||
| Tensor | ||
| gridY g = D.contiguous $ D.view [1, 1, g, g] $ I.t $ D.repeat [g, 1] $ arange' (0 :: Int) g (1 :: Int) |
There was a problem hiding this comment.
https://stackoverflow.com/questions/49643225/whats-the-difference-between-reshape-and-view-in-pytorch
D.contiguous $ D.view is the same as D.reshape
junjihashimoto
force-pushed
the
feature/darknet
branch
from
0b2cec2
to
8aa9b4c
Compare
junjihashimoto
force-pushed
the
feature/darknet
branch
from
8aa9b4c
to
17b0f07
Compare
junjihashimoto
force-pushed
the
feature/darknet
branch
from
72f4438
to
80c90c9
Compare
| loadWeights :: Darknet -> String -> IO Darknet | ||
| loadWeights (Darknet layers) weights_file = do | ||
| System.IO.withFile weights_file System.IO.ReadMode $ \handle -> do | ||
| _ <- BS.hGet handle (5 * 4) -- skip header | ||
| layers' <- forM layers $ \(i,layer) -> do | ||
| let cur_params = flattenParameters layer | ||
| new_params <- forM cur_params $ \param -> loadFloats handle (toDependent param) >>= makeIndependent | ||
| return $ (i,replaceParameters layer new_params) | ||
| return $ Darknet layers' |
There was a problem hiding this comment.
Conv2d/BatchNorm's paramaters are loaded incorrectly.
There was a problem hiding this comment.
Any idea why? I would like to try to do some work on loading pytorch models in the near future as well.
There was a problem hiding this comment.
The data is stored in the weight file as follows.
1, Bias of batchnorm
2, Weight of batchnorm
3, RunningMean of batchnorm
4, RunningVar of batchnorm
5, Weight of Conv2d
Conv2d has no bias.
https://github.com/eriklindernoren/PyTorch-YOLOv3/blob/master/models.py#L282-L317
The list of flattenParameters includes the bias of Conv2d with batchnorm.
Conv2d without batchnorm has bias.
Loader customization is needed.
There was a problem hiding this comment.
It may be easier to fix the ADT.
