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
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
julienChemillier
ae9d72a6eb
Fix Mutlithreading issue with pooling
2023-02-02 14:05:26 +01:00
c0ad845c05
Merge branch 'main' of https://github.com/julienChemillier/TIPE.git
2023-02-01 10:53:28 +01:00
julienChemillier
46ce52802e
merge
2023-01-30 09:39:45 +01:00
julienChemillier
f4975e8812
Change calloc to malloc
2023-01-29 18:34:21 +01:00
1121d11577
Really exiting
2023-01-29 09:47:29 +01:00
bc18a7cb34
Update utils.c/u
2023-01-29 09:40:55 +01:00
64e1cf0ad5
Implement custom memory management
2023-01-28 22:04:38 +01:00
fe880f9aae
Add copy_network_parameters
2023-01-28 13:09:52 +01:00
f5fdfc6513
Update visualisation.py
2023-01-25 11:19:11 +01:00
220d0a71be
Update backpropagation (It works now)
2023-01-25 11:18:47 +01:00
a08750e00e
Fix error handling
2023-01-23 21:24:55 +01:00
b75388f463
Add CNN to webserver
2023-01-23 21:16:36 +01:00
e11d1f552a
Update learning_rate
2023-01-21 19:11:08 +01:00
7deef7c5c5
Add simple_one
2023-01-21 18:59:59 +01:00
5f47b93672
Add loss computation
2023-01-20 13:41:38 +01:00
julienChemillier
c994dab6d9
Change in parameters of 'generate_wanted_output'
2023-01-18 10:31:59 +01:00
julienChemillier
a21481d1cc
Change 'wanted_number' from float to int
2023-01-18 10:25:46 +01:00
4f946cf888
Fix neuron_io
2023-01-17 17:01:16 +01:00
cea4132e2d
Remove white spaces
2023-01-17 15:34:29 +01:00
julienChemillier
7fdd869d6e
Fix Kernel size
2023-01-17 15:25:34 +01:00
f468883eb1
Update scripts
2023-01-17 15:08:47 +01:00
cfa89dc99e
Typo
2023-01-17 15:06:39 +01:00
61468044a9
Update train.c
2023-01-17 12:50:35 +01:00
6917711271
Update the way of reading the network
2023-01-17 12:50:13 +01:00
c78c8a0ade
Update linearisation detection
2023-01-17 12:49:35 +01:00
julienChemillier
721d9597d4
Fix indices error
2023-01-15 17:51:23 +01:00
julienChemillier
3c611d5681
Fix size of network->kernel
2023-01-15 17:51:02 +01:00
771d69af20
Fix dataset memory leak
2023-01-14 15:28:02 +01:00
df48b92cf2
Fix various multithreading related issues
2023-01-14 15:02:57 +01:00
dd6fb046c7
Fix various memory leaks in mnist NN
2023-01-14 14:52:40 +01:00
48dcded57a
Fix unauthorized read
2023-01-14 14:30:59 +01:00
b6aafbf0fd
Fix various memory leaks
2023-01-14 14:30:34 +01:00
2ac811ca78
Add linearisation variable to neuron_io
2023-01-13 22:19:06 +01:00
b5c4384e42
Rename variable
2023-01-13 22:17:37 +01:00
df39c2c299
Add colors
2023-01-13 15:58:46 +01:00
f1c7246d77
Typo
2023-01-13 15:58:26 +01:00
03ad4b01e5
Use OpenMP instead of clock time
...
It was previously not accurate when using threads
2023-01-13 15:58:11 +01:00
julienChemillier
c914370103
Fix linearisation variable
2023-01-11 12:09:41 +01:00
9dfcba3551
Update benchmark tests
2023-01-04 11:00:51 +01:00
d0d68c7afd
Update cuda benchmark
2023-01-04 10:52:39 +01:00
047a24ca9f
Add convolution benchmark [CUDA]
2023-01-04 10:50:55 +01:00
7af686345a
Update comments
2022-12-19 15:49:18 +01:00
c913bf3195
Update train.c
2022-12-19 15:49:03 +01:00
4656c04ad9
Add mnist & webserver documentation
2022-12-09 22:18:58 +01:00
cedb240df2
Add recovery option
2022-12-07 13:09:39 +01:00
963a4afcff
Add cnn knuth shuffle
2022-12-07 10:44:28 +01:00
julienChemillier
c74d3f574b
Merge branch 'main' of https://github.com/julienChemillier/TIPE
2022-12-07 10:27:52 +01:00
ffc0c6ea9f
Add knuth shuffle
2022-11-30 11:24:37 +01:00
e584dfc791
Add test-network option implementation
2022-11-30 10:21:56 +01:00
7da3544d8b
Add recognize option
2022-11-25 15:17:47 +01:00
julienChemillier
c1283d8c4b
Fix softmax_backward
2022-11-25 14:49:21 +01:00
88bec19189
Update neuron_io.c
2022-11-23 11:45:28 +01:00
4cafabdbee
Update train.c
2022-11-23 11:37:26 +01:00
11ce67f845
Update multithreading
2022-11-23 10:41:19 +01:00
18900f3fe9
Change images aspect ration
2022-11-19 22:22:24 +01:00
cfb3cb28d7
Add cnn/preview.c
2022-11-19 17:39:56 +01:00
d0b7781695
Add jpeg dataset implementation
2022-11-19 16:09:07 +01:00
5a0f807a00
Update update.c
2022-11-18 14:09:49 +01:00
d03f7493b2
Move update
2022-11-16 10:38:01 +01:00
julienChemillier
50af676027
Learning_rate is a (NON NULL) float
2022-11-15 18:15:18 +01:00
3e7309c6e1
Add current_accuracy estimation
2022-11-15 17:50:33 +01:00
julienChemillier
f5f22c6b3e
Fix issues
2022-11-15 12:58:00 +01:00
julienChemillier
d94f61bb77
First results in backprop ?
2022-11-15 12:50:38 +01:00
julienChemillier
c73d4d5b90
Fix 'nan' issue
2022-11-15 12:47:33 +01:00
julienChemillier
65505858da
Update backprop
2022-11-12 14:20:13 +01:00
c0381efa71
Ajout de utils.cu & recoloration des tests
...
Ajout de test.cu:
Suppression de redondances dans le code
Recoloration des tests:
Ajout de couleurs pour clarifier le bon fonctionnement ou non du programme
2022-11-11 11:20:30 +01:00
17bca42253
Update Makefile
2022-11-09 12:55:55 +01:00
julienChemillier
43ffdc1b56
Fix an issue
2022-11-09 10:55:14 +01:00
60473ed567
Update cnn neuron_io
2022-11-08 19:57:27 +01:00
5a34311dfb
Update cnn utils
2022-11-08 19:57:13 +01:00
70e0ed08b7
Update mnist utils
2022-11-08 19:56:58 +01:00
julienChemillier
72919406a0
Fix issues
2022-11-08 18:04:58 +01:00
julienChemillier
0f761d1e0c
Fix of an issue regarding the activation function
2022-11-04 12:56:13 +01:00
julienChemillier
b21ac23673
Add of the dropout feature
2022-11-04 12:02:00 +01:00
julienChemillier
682715d5d7
Add learning_rate missing
2022-11-04 11:31:34 +01:00
julienChemillier
7a0ee3be7b
Implementation of the initialisation
2022-11-04 10:54:32 +01:00
julienChemillier
dffc1598ff
Use of 'linearisation' variable
2022-11-04 08:31:58 +01:00
88ff365c70
Clean compilers warnings a bit
2022-11-03 18:45:38 +01:00
4637d62e73
Update backpropagation.c
2022-11-03 18:13:01 +01:00
julienChemillier
698d5820cd
Add backpropagation (.h and .c)
2022-11-03 17:50:11 +01:00
julienChemillier
df8d4f264e
Deletion of last_d_bias and last_d_weights
2022-11-03 16:29:53 +01:00
julienChemillier
0e317549a5
Creation of update (.h and .c)
2022-11-03 16:28:03 +01:00
f30cf0229a
Fix convolution
2022-11-03 11:26:08 +01:00
julienChemillier
ac76fa3f8b
Fix of an error
2022-11-03 11:04:47 +01:00
ee6b6c7fc4
Update convolution.cu
...
Fix compilation with `extern "C" { ... }`
2022-11-03 10:05:21 +01:00
julienChemillier
59a536aad7
Add print files (non tested)
2022-11-01 18:06:52 +01:00
1608256e43
Add cuda convolution
2022-11-01 17:24:29 +01:00
julienChemillier
a1dba81e17
Add 'get_function_activation' function
2022-11-01 11:20:17 +01:00
julienChemillier
3d63e9e63b
Updates in comments
2022-11-01 10:10:43 +01:00
julienChemillier
d5c7c03f82
Add of input_z and and fix of issues
2022-10-31 20:08:42 +01:00
julienChemillier
d6d69a1acb
Add functions for batches (non tested)
2022-10-26 18:27:46 +02:00
julienChemillier
816f7ea334
Add 'get_function_activation' function
2022-10-26 17:32:54 +02:00
3d812701f7
New implementation of CUDA matrix multiplication
2022-10-25 17:49:58 +02:00
cf050de1d6
Move to Makefile
2022-10-24 12:54:51 +02:00
757d641580
Remove unused CUDA code
2022-10-21 14:22:57 +02:00
6ebbfda127
Update matrix_multiplication.cu
2022-10-19 13:05:59 +02:00
0f5867ebb6
Remove parallel
2022-10-19 13:04:57 +02:00
a9e704a7bc
Update matrix_multiplication
2022-10-14 19:56:39 +02:00
