|
|
870b121c2a
|
Switch model and module members to protected
|
2024-05-19 20:21:54 +02:00 |
|
|
|
33d4a43dca
|
Update concat layer
|
2024-05-19 20:21:13 +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 |
|
|
|
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 |
|
|
|
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 |
|
|
|
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 |
|
|
|
a32c737785
|
Allocate activation on heap
|
2024-04-22 18:59:16 +02:00 |
|
|
|
942ee6a32b
|
Add layer name to vector
|
2024-04-21 12:20:02 +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 |
|
|
|
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 |
|
|
|
18522c2dea
|
Cleanup and refactor
|
2024-04-11 22:52:41 +02:00 |
|
|
|
4b9d123e94
|
Implement device vector utils
|
2024-04-11 22:22:33 +02:00 |
|
|
|
710a33bdde
|
Move softmax partial kernels to matmul
|
2024-04-11 22:01:47 +02:00 |
|
|
|
e86e04f6d6
|
Add clearing kernel
|
2024-04-11 19:49:09 +02:00 |
|
|
|
b49dddf34a
|
Improve softmax numerical stability
|
2024-04-08 23:25:46 +02:00 |
|
|
|
e419a93408
|
Fix softmax sum kernel
|
2024-04-08 22:09:18 +02:00 |
|
|
|
9482d7bc43
|
Add model predict test
|
2024-03-22 22:31:32 +01:00 |
|
|
|
87db47089e
|
Add output layer to model predict
|
2024-03-21 23:22:12 +01:00 |
|
|
|
90fb104dae
|
Implement output layer
|
2024-03-21 23:07:46 +01:00 |
|
|
|
a9d0a0832a
|
Change model input layer creation
|
2024-03-21 00:24:49 +01:00 |
|
|
|
af6838e8ae
|
Initial model implementation
|
2024-03-20 22:31:39 +01:00 |
|
|
|
6f4cdf3792
|
Implement avg pool test
|
2024-03-20 21:57:22 +01:00 |
|
|
|
dfff0360d9
|
Implement max pooling test
|
2024-03-20 21:44:04 +01:00 |
|
|
|
ef63cbd9f1
|
Implement avg pooling
|
2024-03-19 22:33:43 +01:00 |
|
|
|
a0fc1b00ae
|
Implement max pooling layer
|
2024-03-19 22:04:58 +01:00 |
|
|
|
b6c4b7d2ae
|
Refactor layers
|
2024-03-19 21:35:05 +01:00 |
|
|
|
8d14b74f66
|
Implement Add layer
|
2024-03-18 20:37:13 +01:00 |
|
|
|
d9c6c663c8
|
Rename ILayer to WeightedLayer
|
2024-03-18 20:36:52 +01:00 |
|
|
|
6cf604423a
|
Combine padding and conv kernel
|
2024-03-18 19:53:40 +01:00 |
|
|
|
e6d3757312
|
Change unsigned int to int
|
2024-03-18 19:40:00 +01:00 |
|
|
|
aac0c3a826
|
Implement concat layer
|
2024-03-17 21:38:29 +01:00 |
|
|
|
42d646750b
|
Abstract activation and implement softmax
|
2024-03-17 18:37:15 +01:00 |
|
|
|
0c22fac64e
|
Add toplevel CUDANet namespace
|
2024-03-17 16:08:53 +01:00 |
|
|
|
dc86cddeb7
|
Use tiling shmem for mat vec mul kernel
|
2024-03-15 23:33:09 +01:00 |
|
|
|
88f7fff217
|
Add prefix to guards
|
2024-03-13 22:23:23 +01:00 |
|
|
|
7157a27e56
|
Add documentation comments
|
2024-03-12 21:50:06 +01:00 |
|
|
|
708164e4d0
|
Implement simple input layer
|
2024-03-12 21:16:46 +01:00 |
|
|
|
9d91896f13
|
Change forward function to return output pointer
|
2024-03-12 20:50:49 +01:00 |
|
|
|
d2ab78fbc7
|
Add Kernels namespace
|
2024-03-11 21:04:23 +01:00 |
|
