Commit Graph

199 Commits

Author SHA1 Message Date
33d4a43dca Update concat layer 2024-05-19 20:21:13 +02:00
e8bffe22d5 Add inception block A 2024-05-19 18:19:07 +02:00
d0b974dd9f Start implementing Inception v3 2024-05-19 17:43:42 +02:00
2118cd47c3 Ignore jpg and txt files 2024-05-19 17:37:19 +02:00
47fad2d3aa Rename alexnet main 2024-05-19 17:37:04 +02:00
e23ffe1ee1 Remove default constructor from Module 2024-05-19 16:16:57 +02:00
8bb2562c4c Add main include file 2024-05-19 16:16:14 +02:00
4a1c4a5f91 Add epsilon param to batch norm 2024-05-19 15:13:22 +02:00
c84f58b97c Implement modules 2024-05-15 18:52:31 +02:00
7c48ed86d2 Implement vector variance function 2024-05-14 21:58:23 +02:00
33a3c6afcb Fix batch norm layer 2024-05-14 21:42:01 +02:00
da8f3167cb Add utils vector mean function 2024-05-14 21:41:18 +02:00
5c8d3f7e25 Compute mean and variance 2024-04-29 20:55:11 +02:00
0ab623fa23 Implement vector mean calculation 2024-04-28 22:04:15 +02:00
26c12dafc0 Update README 2024-04-28 21:47:12 +02:00
96536a44fd Implement batch norm test 2024-04-28 21:46:42 +02:00
f60d62f6bd Implement batch norm layer 2024-04-28 19:58:00 +02:00
3320f610db Add imagenet class map 2024-04-28 19:03:51 +02:00
1f708f3ea3 Change vector scalar math kernels 2024-04-28 19:03:06 +02:00
69111f6cb1 Add version to model bin format 2024-04-23 19:53:48 +02:00
1592f06121 Add opencv to alexnet usage 2024-04-22 22:56:29 +02:00
88e852a6e5 Fix missing predict argument 2024-04-22 22:04:46 +02:00
157d4c736b Add Alexnet README 2024-04-22 21:59:08 +02:00
9a9b034ce5 Add torch predict function 2024-04-22 21:58:32 +02:00
f3ba519229 Fix alexnet normalization 2024-04-22 21:48:53 +02:00
74262309ad Fix max pooling output size calc 2024-04-22 20:58:02 +02:00
c2acad151b Implement simple model validation 2024-04-22 20:57:40 +02:00
f17debc244 Implement getOutputSize and getInputSize for seq layers 2024-04-22 20:31:58 +02:00
fbf6c44bdd Remove extra cudaFree 2024-04-22 19:05:02 +02:00
a32c737785 Allocate activation on heap 2024-04-22 18:59:16 +02:00
26cea9b12c Fix more cuda memcheck errors 2024-04-21 22:56:55 +02:00
58af95eb25 Remove cudaDeviceReset calls from tests 2024-04-21 22:47:12 +02:00
bdbb3f978e Fix matmul and max reduce memcheck errors 2024-04-21 22:11:02 +02:00
9a6152469a Update activation test 2024-04-21 14:00:43 +02:00
942ee6a32b Add layer name to vector 2024-04-21 12:20:02 +02:00
0170afaf3f Improve cuda error handling 2024-04-21 12:19:19 +02:00
d64a28bc9c Fix model weights export 2024-04-21 00:05:56 +02:00
9c5d853b75 Fix bin file seek offset 2024-04-20 21:30:01 +02:00
5e663b9029 Fix bias in conv layer 2024-04-20 19:09:00 +02:00
d08567a563 Fix weigh bias parsing and better error logging 2024-04-20 18:36:53 +02:00
ecf7416f8e Rework padding size setting 2024-04-20 16:31:28 +02:00
dbaab5652e Ignore .bin files 2024-04-20 15:51:02 +02:00
0807a0f2b8 Export pretrained alexnet 2024-04-20 15:50:12 +02:00
ab10959f35 Start implementing AlexNet 2024-04-18 22:31:14 +02:00
ef3a62f399 Remove hardcoded cuda architecture 2024-04-18 20:44:32 +02:00
c1d93bd008 Update README 2024-04-16 21:41:10 +02:00
432adf57bd Test model weights loading 2024-04-16 21:07:06 +02:00
9fb9d7e8e1 Implement getting layer, weights and biases 2024-04-16 19:09:41 +02:00
f4ae45f867 Start implementing weights import 2024-04-15 22:17:48 +02:00
d8c50116e8 Implement pytorch weights export 2024-04-15 22:17:14 +02:00