hexone2086/asmo_vhead
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update README.md

Browse Source
This commit is contained in:
amshaker
2023-07-26 00:59:51 +04:00
parent 075daf69f8
commit 670dea3e1f
2 changed files with 19 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
README.md
View File

@@ -47,10 +47,10 @@ Self-attention has become a defacto choice for capturing global context in vario
| Model | Top-1 accuracy | #params | GMACs | Latency | Ckpt | CoreML|
|:---------------|:----:|:---:|:--:|:--:|:--:|:--:|
| SwiftFormer-XS | 75.7% | 3.5M | 0.4G | 0.7ms | [XS](https://drive.google.com/file/d/15Ils-U96pQePXQXx2MpmaI-yAceFAr2x/view?usp=sharing) | [XS](https://drive.google.com/file/d/1tZVxtbtAZoLLoDc5qqoUGulilksomLeK/view?usp=sharing) |
| SwiftFormer-S | 78.5% | 6.1M | 1.0G | 0.8ms | [S](https://drive.google.com/file/d/1_0eWwgsejtS0bWGBQS3gwAtYjXdPRGlu/view?usp=sharing) | [S](https://drive.google.com/file/d/13EOCZmtvbMR2V6UjezSZnbBz2_-59Fva/view?usp=sharing) |
| SwiftFormer-L1 | 80.9% | 12.1M | 1.6G | 1.1ms | [L1](https://drive.google.com/file/d/1jlwrwWQ0SQzDRc5adtWIwIut5d1g9EsM/view?usp=sharing) | [L1](https://drive.google.com/file/d/1c3VUsi4q7QQ2ykXVS2d4iCRL478fWF3e/view?usp=sharing) |
| SwiftFormer-L3 | 83.0% | 28.5M | 4.0G | 1.9ms | [L3](https://drive.google.com/file/d/1ypBcjx04ShmPYRhhjBRubiVjbExUgSa7/view?usp=sharing) | [L3](https://drive.google.com/file/d/1svahgIjh7da781jHOHjX58mtzCzYXSsJ/view?usp=sharing) |
| SwiftFormer-XS | 75.7% | 3.5M | 0.6G | 0.7ms | [XS](https://drive.google.com/file/d/12RchxzyiJrtZS-2Bur9k4wcRQMItA43S/view?usp=sharing) | [XS](https://drive.google.com/file/d/1bkAP_BD6CdDqlbQsStZhLa0ST2NZTIvH/view?usp=sharing) |
| SwiftFormer-S | 78.5% | 6.1M | 1.0G | 0.8ms | [S](https://drive.google.com/file/d/1awpcXAaHH38WaHrOmUM8updxQazUZ3Nb/view?usp=sharing) | [S](https://drive.google.com/file/d/1qNAhecWIeQ1YJotWhbnLTCR5Uv1zBaf1/view?usp=sharing) |
| SwiftFormer-L1 | 80.9% | 12.1M | 1.6G | 1.1ms | [L1](https://drive.google.com/file/d/1SDzauVmpR5uExkOv3ajxdwFnP-Buj9Uo/view?usp=sharing) | [L1](https://drive.google.com/file/d/1CowZE7-lbxz93uwXqefe-HxGOHUdvX_a/view?usp=sharing) |
| SwiftFormer-L3 | 83.0% | 28.5M | 4.0G | 1.9ms | [L3](https://drive.google.com/file/d/1DAxMe6FlnZBBIpR-HYIDfFLWJzIgiF0Y/view?usp=sharing) | [L3](https://drive.google.com/file/d/1SO3bRWd9oWJemy-gpYUcwP-B4bJ-dsdg/view?usp=sharing) |
## Detection and Segmentation Qualitative Results
@@ -77,6 +77,7 @@ conda activate swiftformer
pip install torch==1.11.0+cu113 torchvision==0.12.0+cu113 --extra-index-url https://download.pytorch.org/whl/cu113
pip install timm
pip install coremltools==5.2.0
```
### Data preparation

31
models/swiftformer.py
View File

@@ -25,9 +25,6 @@ SwiftFormer_depth = {
'l3': [4, 4, 12, 6],
}
CoreMLConversion = False
def stem(in_chs, out_chs):
"""
Stem Layer that is implemented by two layers of conv.
@@ -144,8 +141,8 @@ class Mlp(nn.Module):
class EfficientAdditiveAttnetion(nn.Module):
"""
Efficient Additive Attention module for SwiftFormer.
Input: tensor in shape [B, C, H, W]
Output: tensor in shape [B, C, H, W]
Input: tensor in shape [B, N, D]
Output: tensor in shape [B, N, D]
"""
def __init__(self, in_dims=512, token_dim=256, num_heads=2):
@@ -163,26 +160,23 @@ class EfficientAdditiveAttnetion(nn.Module):
query = self.to_query(x)
key = self.to_key(x)
if not CoreMLConversion:
# torch.nn.functional.normalize is not supported by the ANE of iPhone devices.
# Using this layer improves the accuracy by ~0.1-0.2%
query = torch.nn.functional.normalize(query, dim=-1)
key = torch.nn.functional.normalize(key, dim=-1)
query = torch.nn.functional.normalize(query, dim=-1) #BxNxD
key = torch.nn.functional.normalize(key, dim=-1) #BxNxD
query_weight = query @ self.w_g
A = query_weight * self.scale_factor
query_weight = query @ self.w_g # BxNx1 (BxNxD @ Dx1)
A = query_weight * self.scale_factor # BxNx1
A = A.softmax(dim=-1)
A = torch.nn.functional.normalize(A, dim=1) # BxNx1
G = torch.sum(A * query, dim=1)
G = torch.sum(A * query, dim=1) # BxD
G = einops.repeat(
G, "b d -> b repeat d", repeat=key.shape[1]
)
) # BxNxD
out = self.Proj(G * key) + query
out = self.Proj(G * key) + query #BxNxD
out = self.final(out)
out = self.final(out) # BxNxD
return out
@@ -215,6 +209,7 @@ class SwiftFormerLocalRepresentation(nn.Module):
nn.init.constant_(m.bias, 0)
def forward(self, x):
print("SwiftFormerLocalRepresentation input is ", x.shape)
input = x
x = self.dwconv(x)
x = self.norm(x)
@@ -225,6 +220,7 @@ class SwiftFormerLocalRepresentation(nn.Module):
x = input + self.drop_path(self.layer_scale * x)
else:
x = input + self.drop_path(x)
return x
@@ -505,3 +501,4 @@ def SwiftFormer_L3(pretrained=False, **kwargs):
**kwargs)
model.default_cfg = _cfg(crop_pct=0.9)
return model