18 Commits

Author SHA1 Message Date
d63fb2c870 cnn/make: Fix misaligned address 2023-05-28 09:26:12 +02:00
0fb23c9b15 cnn/make:dense_linearized: fix wrong indices 2023-05-15 12:51:00 +02:00
a7df405d08 Fixes for cuda compilation following 3b9ad3d 2023-05-14 18:12:52 +02:00
julienChemillier
3b9ad3db4d Merge of function in 'src/common/include/utils.h' 2023-05-14 15:56:58 +02:00
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
3dd2e33fa9 Fix issues with the network not converging 2023-05-13 15:39:22 +02:00
julienChemillier
f316882eeb Add 'stride' and 'padding' to the forward 2023-05-13 13:37:46 +02:00
fd36226600 Move generic files to src/common 2023-05-12 16:16:34 +02:00
julienChemillier
af288166d6 Ajout stride dans average_ pooling et max_pooling 2023-05-08 11:32:58 +02:00
eeff720ae4 Add CUDA blocksize to config.h 2023-03-28 12:54:49 +02:00
7d7cd2e3a7 Fix FLT_MIN misuses 2023-03-10 18:20:10 +01:00
julienChemillier
9d2d61703d Replace min_float by fminf 2023-03-09 14:27:23 +01:00
9d54b1e4ea Rename variables 2023-03-03 21:59:51 +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
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
0aa6fbc5f0 Full implementation of forward convolution in CUDA 2023-02-15 11:42:24 +01:00