321994df2b
Fix cuda compilation
2023-05-13 22:42:13 +02:00
julienChemillier
c0808b9240
Change notation toward a consensus
2023-05-13 17:22:47 +02:00
julienChemillier
521a1bb729
Add definition of 'convolution_not_outside'
2023-05-13 15:50:01 +02:00
julienChemillier
f316882eeb
Add 'stride' and 'padding' to the forward
2023-05-13 13:37:46 +02:00
julienChemillier
a68805894f
Change in comments of 'free.c' and 'free.h'
2023-05-13 11:17:32 +02:00
693dee581e
Move 'min' and 'max' definition to commons/utils
2023-05-12 16:17:47 +02:00
7c2c911976
cnn/export.c: Ajout de visual-propagation
...
Cette option permet de visualiser l'état des différentes couches
après propagation sur une image donnée
(fonctionne uniquement sur des datasets MNIST pour le moment)
2023-05-08 18:53:04 +02:00
julienChemillier
af288166d6
Ajout stride dans average_ pooling et max_pooling
2023-05-08 11:32:58 +02:00
julienChemillier
6e022fbd44
Ajout de 'stride' dans 'make_convolution'
2023-05-08 11:11:55 +02:00
3198e6f2d0
Load image from a separate thread
2023-04-02 17:34:31 +02:00
710306a286
Remove duplicated functions
2023-03-31 15:16:53 +02:00
7511856621
Translate backward convolution to CUDA
...
Not working yet, CUDA kernels in `backpropagation.cu` don't have access to activation functions declared in `function.cu` using `get_activation_function_cuda`.
Temporary workaround: copy `backpropagation.cu` parts that don't work to `function.cu` (all the parts using function pointers in kernels
2023-03-30 18:16:41 +02:00
5088c415d6
Add comments to config.h
2023-03-30 18:11:19 +02:00
dd16e34cce
extern "C" get_activation_function_cuda
2023-03-30 18:11:00 +02:00
eeff720ae4
Add CUDA blocksize to config.h
2023-03-28 12:54:49 +02:00
julienChemillier
5f684d9f91
Implementation of Adam Optimizer
2023-03-27 18:17:50 +02:00
677de892e7
Add function.cu
...
Translate `apply_function_input` and `get_activation_function` to CUDA
2023-03-26 17:14:07 +02:00
e4003aea28
Add config.h
2023-03-24 15:21:57 +01:00
7da6541937
Rename BOUND_RELU to RELU_CLIP_VALUE
2023-03-24 15:12:31 +01:00
b893f11da0
Add random offset to mnist images during learning
2023-03-22 13:03:19 +01:00
julienChemillier
1bd92074ab
Back to multiple bias implementation
2023-03-18 13:25:58 +01:00
00ac29b1d0
Update train.h parameters
2023-03-17 15:46:30 +01:00
c078d75ca6
Rename mnist network to dense for consistency
2023-03-15 21:27:57 +01:00
julienChemillier
84e05a732b
Change of a line
2023-03-13 18:47:32 +01:00
julienChemillier
2a88621c34
Change bias implementation to fix keras's one
2023-03-12 11:13:26 +01:00
3a50b08179
Add max_pooling backward
2023-03-10 18:19:23 +01:00
julienChemillier
9d2d61703d
Replace min_float by fminf
2023-03-09 14:27:23 +01:00
julienChemillier
fec4651946
Add 3 new types of initialisation
2023-03-09 06:57:51 +01:00
julienChemillier
89402b9ee6
Replace numbers by defines
2023-03-08 20:48:34 +01:00
796a94207f
Add comments to cnn.c
2023-03-03 21:58:05 +01:00
177aaa869c
Reduce redundancy in function.c
2023-03-03 21:56:42 +01:00
7f88acf17f
Add float clip(float)
to update.c
2023-03-02 10:35:25 +01:00
c45b21e322
Rename MAX_RESEAU to CLIP_VALUE
2023-03-01 19:12:57 +01:00
4b87b19188
Add bias to make_dense_linearized
2023-02-28 11:47:57 +01:00
julienChemillier
4df1bf7b5b
Suppression de warning durant la compilation
2023-02-24 11:03:51 +01:00
julienChemillier
b7b90f9cab
Add cross_entropy backpropagation
2023-02-24 11:01:59 +01:00
6071a3608b
Improve consistency across headers
2023-02-19 15:08:02 +01:00
julienChemillier
76f17371de
Change of documention in 'struct.h'
2023-02-19 13:54:00 +01:00
julienChemillier
c13772c291
Change 'w' and 'd_w' to 'weights' and 'd_weights'
2023-02-19 13:38:33 +01:00
julienChemillier
9ed53ceabb
Change 'output_units' to 'size_output'
2023-02-19 12:53:08 +01:00
julienChemillier
c67d2bf697
Change 'input_units' to 'size_input'
2023-02-19 12:50:27 +01:00
julienChemillier
3d1a5a5021
Add 'leaky_relu' activation function
2023-02-19 12:13:03 +01:00
63ef37dc56
Add count_null_weights
2023-02-19 10:22:42 +01:00
f60a80f8c5
Fix typo
2023-02-18 13:10:42 +01:00
julienChemillier
3f9114c245
Change fully_connected to dense
2023-02-17 14:56:05 +01:00
julienChemillier
98290092dc
Merge branch 'main' of https://github.com/julienChemillier/TIPE
2023-02-17 14:53:19 +01:00
julienChemillier
b3a6ecbfec
Deletion of a useless parameter in initialisation
2023-02-17 14:35:58 +01:00
0aa6fbc5f0
Full implementation of forward convolution in CUDA
2023-02-15 11:42:24 +01:00
b18fd7aab9
Update headers
2023-02-04 13:12:52 +01:00
julienChemillier
33f85baa1e
Fix issues due to pooling
2023-02-03 15:12:59 +01:00