Created
April 3, 2023 14:42
-
-
Save laksjdjf/d3eba3e58351188bea84c90eebb122c9 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| ============================================================================================================== | |
| Layer (type (var_name)) Input Shape Output Shape | |
| ============================================================================================================== | |
| UNetModel (UNetModel) [1, 4, 64, 64] [1, 4, 64, 64] | |
| ├─Sequential (time_embed) [1, 320] [1, 1280] | |
| │ └─Linear (0) [1, 320] [1, 1280] | |
| │ └─SiLU (1) [1, 1280] [1, 1280] | |
| │ └─Linear (2) [1, 1280] [1, 1280] | |
| ├─ModuleList (input_blocks) -- -- | |
| │ └─TimestepEmbedSequential (0) [1, 4, 64, 64] [1, 320, 64, 64] | |
| │ │ └─Conv2d (0) [1, 4, 64, 64] [1, 320, 64, 64] | |
| │ └─TimestepEmbedSequential (1) [1, 320, 64, 64] [1, 320, 64, 64] | |
| │ │ └─ResBlock (0) [1, 320, 64, 64] [1, 320, 64, 64] | |
| │ │ └─SpatialTransformer (1) [1, 320, 64, 64] [1, 320, 64, 64] | |
| │ └─TimestepEmbedSequential (2) [1, 320, 64, 64] [1, 320, 64, 64] | |
| │ │ └─ResBlock (0) [1, 320, 64, 64] [1, 320, 64, 64] | |
| │ │ └─SpatialTransformer (1) [1, 320, 64, 64] [1, 320, 64, 64] | |
| │ └─TimestepEmbedSequential (3) [1, 320, 64, 64] [1, 320, 32, 32] | |
| │ │ └─Downsample (0) [1, 320, 64, 64] [1, 320, 32, 32] | |
| │ └─TimestepEmbedSequential (4) [1, 320, 32, 32] [1, 640, 32, 32] | |
| │ │ └─ResBlock (0) [1, 320, 32, 32] [1, 640, 32, 32] | |
| │ │ └─SpatialTransformer (1) [1, 640, 32, 32] [1, 640, 32, 32] | |
| │ └─TimestepEmbedSequential (5) [1, 640, 32, 32] [1, 640, 32, 32] | |
| │ │ └─ResBlock (0) [1, 640, 32, 32] [1, 640, 32, 32] | |
| │ │ └─SpatialTransformer (1) [1, 640, 32, 32] [1, 640, 32, 32] | |
| │ └─TimestepEmbedSequential (6) [1, 640, 32, 32] [1, 640, 16, 16] | |
| │ │ └─Downsample (0) [1, 640, 32, 32] [1, 640, 16, 16] | |
| │ └─TimestepEmbedSequential (7) [1, 640, 16, 16] [1, 1280, 16, 16] | |
| │ │ └─ResBlock (0) [1, 640, 16, 16] [1, 1280, 16, 16] | |
| │ │ └─SpatialTransformer (1) [1, 1280, 16, 16] [1, 1280, 16, 16] | |
| │ └─TimestepEmbedSequential (8) [1, 1280, 16, 16] [1, 1280, 16, 16] | |
| │ │ └─ResBlock (0) [1, 1280, 16, 16] [1, 1280, 16, 16] | |
| │ │ └─SpatialTransformer (1) [1, 1280, 16, 16] [1, 1280, 16, 16] | |
| │ └─TimestepEmbedSequential (9) [1, 1280, 16, 16] [1, 1280, 8, 8] | |
| │ │ └─Downsample (0) [1, 1280, 16, 16] [1, 1280, 8, 8] | |
| │ └─TimestepEmbedSequential (10) [1, 1280, 8, 8] [1, 1280, 8, 8] | |
| │ │ └─ResBlock (0) [1, 1280, 8, 8] [1, 1280, 8, 8] | |
| │ └─TimestepEmbedSequential (11) [1, 1280, 8, 8] [1, 1280, 8, 8] | |
| │ │ └─ResBlock (0) [1, 1280, 8, 8] [1, 1280, 8, 8] | |
| ├─TimestepEmbedSequential (middle_block) [1, 1280, 8, 8] [1, 1280, 8, 8] | |
| │ └─ResBlock (0) [1, 1280, 8, 8] [1, 1280, 8, 8] | |
| │ │ └─Sequential (in_layers) [1, 1280, 8, 8] [1, 1280, 8, 8] | |
| │ │ └─Sequential (emb_layers) [1, 1280] [1, 1280] | |
| │ │ └─Sequential (out_layers) [1, 1280, 8, 8] [1, 1280, 8, 8] | |
| │ │ └─Identity (skip_connection) [1, 1280, 8, 8] [1, 1280, 8, 8] | |
| │ └─SpatialTransformer (1) [1, 1280, 8, 8] [1, 1280, 8, 8] | |
| │ │ └─GroupNorm (norm) [1, 1280, 8, 8] [1, 1280, 8, 8] | |
| │ │ └─Linear (proj_in) [1, 64, 1280] [1, 64, 1280] | |
| │ │ └─ModuleList (transformer_blocks) -- -- | |
| │ │ └─Linear (proj_out) [1, 64, 1280] [1, 64, 1280] | |
| │ └─ResBlock (2) [1, 1280, 8, 8] [1, 1280, 8, 8] | |
| │ │ └─Sequential (in_layers) [1, 1280, 8, 8] [1, 1280, 8, 8] | |
| │ │ └─Sequential (emb_layers) [1, 1280] [1, 1280] | |
| │ │ └─Sequential (out_layers) [1, 1280, 8, 8] [1, 1280, 8, 8] | |
| │ │ └─Identity (skip_connection) [1, 1280, 8, 8] [1, 1280, 8, 8] | |
| ├─ModuleList (output_blocks) -- -- | |
| │ └─TimestepEmbedSequential (0) [1, 2560, 8, 8] [1, 1280, 8, 8] | |
| │ │ └─ResBlock (0) [1, 2560, 8, 8] [1, 1280, 8, 8] | |
| │ └─TimestepEmbedSequential (1) [1, 2560, 8, 8] [1, 1280, 8, 8] | |
| │ │ └─ResBlock (0) [1, 2560, 8, 8] [1, 1280, 8, 8] | |
| │ └─TimestepEmbedSequential (2) [1, 2560, 8, 8] [1, 1280, 16, 16] | |
| │ │ └─ResBlock (0) [1, 2560, 8, 8] [1, 1280, 8, 8] | |
| │ │ └─Upsample (1) [1, 1280, 8, 8] [1, 1280, 16, 16] | |
| │ └─TimestepEmbedSequential (3) [1, 2560, 16, 16] [1, 1280, 16, 16] | |
| │ │ └─ResBlock (0) [1, 2560, 16, 16] [1, 1280, 16, 16] | |
| │ │ └─SpatialTransformer (1) [1, 1280, 16, 16] [1, 1280, 16, 16] | |
| │ └─TimestepEmbedSequential (4) [1, 2560, 16, 16] [1, 1280, 16, 16] | |
| │ │ └─ResBlock (0) [1, 2560, 16, 16] [1, 1280, 16, 16] | |
| │ │ └─SpatialTransformer (1) [1, 1280, 16, 16] [1, 1280, 16, 16] | |
| │ └─TimestepEmbedSequential (5) [1, 1920, 16, 16] [1, 1280, 32, 32] | |
| │ │ └─ResBlock (0) [1, 1920, 16, 16] [1, 1280, 16, 16] | |
| │ │ └─SpatialTransformer (1) [1, 1280, 16, 16] [1, 1280, 16, 16] | |
| │ │ └─Upsample (2) [1, 1280, 16, 16] [1, 1280, 32, 32] | |
| │ └─TimestepEmbedSequential (6) [1, 1920, 32, 32] [1, 640, 32, 32] | |
| │ │ └─ResBlock (0) [1, 1920, 32, 32] [1, 640, 32, 32] | |
| │ │ └─SpatialTransformer (1) [1, 640, 32, 32] [1, 640, 32, 32] | |
| │ └─TimestepEmbedSequential (7) [1, 1280, 32, 32] [1, 640, 32, 32] | |
| │ │ └─ResBlock (0) [1, 1280, 32, 32] [1, 640, 32, 32] | |
| │ │ └─SpatialTransformer (1) [1, 640, 32, 32] [1, 640, 32, 32] | |
| │ └─TimestepEmbedSequential (8) [1, 960, 32, 32] [1, 640, 64, 64] | |
| │ │ └─ResBlock (0) [1, 960, 32, 32] [1, 640, 32, 32] | |
| │ │ └─SpatialTransformer (1) [1, 640, 32, 32] [1, 640, 32, 32] | |
| │ │ └─Upsample (2) [1, 640, 32, 32] [1, 640, 64, 64] | |
| │ └─TimestepEmbedSequential (9) [1, 960, 64, 64] [1, 320, 64, 64] | |
| │ │ └─ResBlock (0) [1, 960, 64, 64] [1, 320, 64, 64] | |
| │ │ └─SpatialTransformer (1) [1, 320, 64, 64] [1, 320, 64, 64] | |
| │ └─TimestepEmbedSequential (10) [1, 640, 64, 64] [1, 320, 64, 64] | |
| │ │ └─ResBlock (0) [1, 640, 64, 64] [1, 320, 64, 64] | |
| │ │ └─SpatialTransformer (1) [1, 320, 64, 64] [1, 320, 64, 64] | |
| │ └─TimestepEmbedSequential (11) [1, 640, 64, 64] [1, 320, 64, 64] | |
| │ │ └─ResBlock (0) [1, 640, 64, 64] [1, 320, 64, 64] | |
| │ │ └─SpatialTransformer (1) [1, 320, 64, 64] [1, 320, 64, 64] | |
| ├─Sequential (out) [1, 320, 64, 64] [1, 4, 64, 64] | |
| │ └─GroupNorm32 (0) [1, 320, 64, 64] [1, 320, 64, 64] | |
| │ └─SiLU (1) [1, 320, 64, 64] [1, 320, 64, 64] | |
| │ └─Conv2d (2) [1, 320, 64, 64] [1, 4, 64, 64] | |
| ============================================================================================================== |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment