julienChemillier
fa169e3a37
Removal of useless comments
2023-05-13 10:36:27 +02:00
julienChemillier
0a63988d3c
Removal of useless comments
2023-05-13 10:30:29 +02:00
julienChemillier
2790883586
Removal of warnings
2023-05-13 10:05:54 +02:00
47a475a370
Removed extra memory allocation
2023-05-12 16:26:26 +02:00
49a2299c1c
Revert fd36226 for cnn/creation.c
2023-05-12 16:21:14 +02:00
693dee581e
Move 'min' and 'max' definition to commons/utils
2023-05-12 16:17:47 +02:00
fd36226600
Move generic files to src/common
2023-05-12 16:16:34 +02:00
e44cecbe8d
Add jpeg support to export.c
2023-05-12 14:50:22 +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
953c92ac61
Check for errors
2023-03-30 18:08:31 +02:00
2ee1bc4079
Add reset_3d_array function
2023-03-30 18:08:13 +02:00
eeff720ae4
Add CUDA blocksize to config.h
2023-03-28 12:54:49 +02:00
2d6b4fe011
Implement copy_3d_array in CUDA
2023-03-28 12:38:06 +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
bb0c709a50
Remove unusable arguments from dense network
2023-03-15 21:34:30 +01:00
c078d75ca6
Rename mnist network to dense for consistency
2023-03-15 21:27:57 +01:00
8e411e29f4
Update webserver
2023-03-14 15:20:40 +01:00
julienChemillier
84e05a732b
Change of a line
2023-03-13 18:47:32 +01:00
julienChemillier
adeee56f83
Merge branch 'main' of https://github.com/julienChemillier/TIPE
2023-03-13 18:46:31 +01:00
04087c3de4
Rename mnist folder to dense
2023-03-13 13:55:09 +01:00
julienChemillier
b3bc4b7787
Removal of useless variables
2023-03-13 13:43:42 +01:00
julienChemillier
2a88621c34
Change bias implementation to fix keras's one
2023-03-12 11:13:26 +01:00
julienChemillier
fa7d8b2dbc
Add identity as activation function
2023-03-12 09:34:06 +01:00
julienChemillier
179a372159
Fix backpropagation error
2023-03-11 19:40:25 +01:00
julienChemillier
21ee3430c5
Update backpropation of max_pooling
2023-03-11 19:36:46 +01:00
3e57054215
Add webserver/guess
2023-03-11 17:51:52 +01:00
81ff4f4d00
Trying to improve train.c readability
2023-03-11 13:45:00 +01:00
7d7cd2e3a7
Fix FLT_MIN misuses
2023-03-10 18:20:10 +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
91e4a1b316
Fix creation.c
2023-03-08 20:59:53 +01:00
julienChemillier
89402b9ee6
Replace numbers by defines
2023-03-08 20:48:34 +01:00
c9a890a20a
This workaround seems better
...
See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66425#c34
2023-03-03 22:14:42 +01:00
6362382e91
Remove warning [-Wunused-result]
2023-03-03 22:06:09 +01:00
9d54b1e4ea
Rename variables
2023-03-03 21:59:51 +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
95ce123587
Fix wrong argument for pooling (forward)
2023-03-01 09:37:40 +01:00
87b37aee80
Update benchmark scripts
2023-02-28 13:16:39 +01:00
1db6c6824d
Fix typo
2023-02-28 13:15:16 +01:00
79312caace
Use printf_error and printf_warning when needed
2023-02-28 13:14:51 +01:00
4b87b19188
Add bias to make_dense_linearized
2023-02-28 11:47:57 +01:00
c1b4f55929
Fix *average* pooling
2023-02-27 18:53:13 +01:00
9b8aa1caf8
Add loss information
2023-02-24 14:36:48 +01:00
e1fff4089b
Update benchmark_binary.py
2023-02-24 11:48:02 +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
b89c651174
Align memory addresses when allocating for CUDA
...
https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#device-memory-accesses
2023-02-22 15:08:14 +01:00
a049f578af
Add print_memory & fix gree
2023-02-19 16:28:34 +01:00
6071a3608b
Improve consistency across headers
2023-02-19 15:08:02 +01:00
5bd5397356
Remove some warnings
2023-02-19 15:02:21 +01:00
383d3bebfd
Check device memory block size
...
& add pretty-prints
& remove some warnings
2023-02-19 15:01:58 +01:00
julienChemillier
76f17371de
Change of documention in 'struct.h'
2023-02-19 13:54:00 +01:00
julienChemillier
1d462576a9
Change 'input_size' to 'size_input'
2023-02-19 13:43:09 +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
6a98d2d9cf
Add cuda_memory_management test
2023-02-19 10:31:19 +01:00
2d46136609
Fix memory_management not used in CUDA
2023-02-19 10:28:18 +01:00
63ef37dc56
Add count_null_weights
2023-02-19 10:22:42 +01:00
db92b367ad
Fix abusive unnecessary use of shared memory
2023-02-19 10:22:22 +01:00
e181deab1e
Fix gree
2023-02-18 14:10:52 +01:00
1fdb9ff37a
Fix get_length calling the wrong function
2023-02-18 14:06:01 +01:00
julienChemillier
444f2b5931
Merge branch 'main' of https://github.com/julienChemillier/TIPE
2023-02-18 13:27:05 +01:00
julienChemillier
a461e0756a
Oupsi
2023-02-18 13:26:26 +01:00
f60a80f8c5
Fix typo
2023-02-18 13:10:42 +01:00
5c7c013d91
Change headers
2023-02-18 13:10:00 +01:00
795d8b68d7
Add custom memory_management
2023-02-18 13:03:08 +01:00
julienChemillier
62fe4deeca
Change 'fully_connected' to 'dense'
2023-02-18 12:53:38 +01:00
julienChemillier
866e2f9a16
Fix non defined variable in initialisation.c
2023-02-17 18:13:59 +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
a9262cacc1
Simplify extern "C" expressions
2023-02-15 11:22:51 +01:00
16a9cafc18
Update neuron_io.c to save larger networks
2023-02-10 14:55:08 +01:00
b3b918aa4f
Add benchmark_binary.py
2023-02-07 18:50:28 +01:00
de21f865cb
Change coefficients in visualisation_kernel.py
2023-02-07 18:48:57 +01:00
julienChemillier
4547335ec0
Fix softmax, dense and pooling backprops
2023-02-07 18:39:38 +01:00
835a08cf46
Add generate_binaries.sh
2023-02-06 13:52:41 +01:00
9193257058
Add descriptive comments to convolution
2023-02-05 16:23:47 +01:00
4a2e3cc3f9
Add visualisation_kernel.py
2023-02-05 16:22:50 +01:00
635b46bdf3
Add export.c
2023-02-05 16:21:41 +01:00
