Skip to content

P
PaddleClas

PaddlePaddle / PaddleClas
1 年多 前同步成功

通知 116
Star 4999
Fork 1114
P
PaddleClas
提交 0e807423 编写于 作者: littletomatodonkey's avatar littletomatodonkey
浏览文件
操作

fix bs

上级 bce8ffbe
隐藏空白更改
内联 并排
Showing with 31 addition and 15 deletion
docs/zh_CN/models/DPN_DenseNet.md
浏览文件 @ 0e807423
......@@ -53,7 +53,7 @@ DPN的全称是Dual Path Networks，即双通道网络。该网络是由DenseNet
## 基于T4 GPU的预测速度
| Models | Crop Size | Resize Short Size | FP16<br>batch_size=1<br>(ms) | FP16<br>batch_size=4<br>(ms) | FP16<br>batch_size=8<br>(ms) | FP32<br>batch_size=1<br>(ms) | FP32<br>batch_size=4<br>(ms) | FP32<br>batch_size=8<br>(ms) |
| Models | Crop Size | Resize Short Size | FP16<br>Batch Size=1<br>(ms) | FP16<br>Batch Size=4<br>(ms) | FP16<br>Batch Size=8<br>(ms) | FP32<br>Batch Size=1<br>(ms) | FP32<br>Batch Size=4<br>(ms) | FP32<br>Batch Size=8<br>(ms) |
|-------------|-----------|-------------------|------------------------------|------------------------------|------------------------------|------------------------------|------------------------------|------------------------------|
| DenseNet121 | 224 | 256 | 4.16436 | 7.2126 | 10.50221 | 4.40447 | 9.32623 | 15.25175 |
| DenseNet161 | 224 | 256 | 9.27249 | 14.25326 | 20.19849 | 10.39152 | 22.15555 | 35.78443 |
......
docs/zh_CN/models/EfficientNet_and_ResNeXt101_wsl.md
浏览文件 @ 0e807423
......@@ -60,7 +60,7 @@ ResNeXt是facebook于2016年提出的一种对ResNet的改进版网络。在2019
## 基于T4 GPU的预测速度
| Models | Crop Size | Resize Short Size | FP16<br>batch_size=1<br>(ms) | FP16<br>batch_size=4<br>(ms) | FP16<br>batch_size=8<br>(ms) | FP32<br>batch_size=1<br>(ms) | FP32<br>batch_size=4<br>(ms) | FP32<br>batch_size=8<br>(ms) |
| Models | Crop Size | Resize Short Size | FP16<br>Batch Size=1<br>(ms) | FP16<br>Batch Size=4<br>(ms) | FP16<br>Batch Size=8<br>(ms) | FP32<br>Batch Size=1<br>(ms) | FP32<br>Batch Size=4<br>(ms) | FP32<br>Batch Size=8<br>(ms) |
|---------------------------|-----------|-------------------|------------------------------|------------------------------|------------------------------|------------------------------|------------------------------|------------------------------|
| ResNeXt101_<br>32x8d_wsl | 224 | 256 | 18.19374 | 21.93529 | 34.67802 | 18.52528 | 34.25319 | 67.2283 |
| ResNeXt101_<br>32x16d_wsl | 224 | 256 | 18.52609 | 36.8288 | 62.79947 | 25.60395 | 71.88384 | 137.62327 |
......
docs/zh_CN/models/HRNet.md
浏览文件 @ 0e807423
......@@ -44,7 +44,7 @@ HRNet是2019年由微软亚洲研究院提出的一种全新的神经网络，
## 基于T4 GPU的预测速度
| Models | Crop Size | Resize Short Size | FP16<br>batch_size=1<br>(ms) | FP16<br>batch_size=4<br>(ms) | FP16<br>batch_size=8<br>(ms) | FP32<br>batch_size=1<br>(ms) | FP32<br>batch_size=4<br>(ms) | FP32<br>batch_size=8<br>(ms) |
| Models | Crop Size | Resize Short Size | FP16<br>Batch Size=1<br>(ms) | FP16<br>Batch Size=4<br>(ms) | FP16<br>Batch Size=8<br>(ms) | FP32<br>Batch Size=1<br>(ms) | FP32<br>Batch Size=4<br>(ms) | FP32<br>Batch Size=8<br>(ms) |
|-------------|-----------|-------------------|------------------------------|------------------------------|------------------------------|------------------------------|------------------------------|------------------------------|
| HRNet_W18_C | 224 | 256 | 6.79093 | 11.50986 | 17.67244 | 7.40636 | 13.29752 | 23.33445 |
| HRNet_W30_C | 224 | 256 | 8.98077 | 14.08082 | 21.23527 | 9.57594 | 17.35485 | 32.6933 |
......
docs/zh_CN/models/Inception.md
浏览文件 @ 0e807423
......@@ -37,7 +37,7 @@ InceptionV4是2016年由Google设计的新的神经网络，当时残差结构
## 基于V100 GPU的预测速度
| Models | Crop Size | Resize Short Size | Batch Size=1<br>(ms) |
| Models | Crop Size | Resize Short Size | FP32<br>Batch Size=1<br>(ms) |
|------------------------|-----------|-------------------|--------------------------|
| GoogLeNet | 224 | 256 | 1.807 |
| Xception41 | 299 | 320 | 3.972 |
......@@ -51,7 +51,7 @@ InceptionV4是2016年由Google设计的新的神经网络，当时残差结构
## 基于T4 GPU的预测速度
| Models | Crop Size | Resize Short Size | FP16<br>batch_size=1<br>(ms) | FP16<br>batch_size=4<br>(ms) | FP16<br>batch_size=8<br>(ms) | FP32<br>batch_size=1<br>(ms) | FP32<br>batch_size=4<br>(ms) | FP32<br>batch_size=8<br>(ms) |
| Models | Crop Size | Resize Short Size | FP16<br>Batch Size=1<br>(ms) | FP16<br>Batch Size=4<br>(ms) | FP16<br>Batch Size=8<br>(ms) | FP32<br>Batch Size=1<br>(ms) | FP32<br>Batch Size=4<br>(ms) | FP32<br>Batch Size=8<br>(ms) |
|--------------------|-----------|-------------------|------------------------------|------------------------------|------------------------------|------------------------------|------------------------------|------------------------------|
| GoogLeNet | 299 | 320 | 1.75451 | 3.39931 | 4.71909 | 1.88038 | 4.48882 | 6.94035 |
| Xception41 | 299 | 320 | 2.91192 | 7.86878 | 15.53685 | 4.96939 | 17.01361 | 32.67831 |
......
docs/zh_CN/models/Mobile.md
浏览文件 @ 0e807423
......@@ -59,9 +59,9 @@ MobileNetV3是Google于2019年提出的一种基于NAS的新的轻量级网络
| ShuffleNetV2_swish | 0.700 | 0.892 | | | 0.290 | 2.260 |
## CPU预测速度和存储大小
## 基于SD855的预测速度和存储大小
| Models | batch_size=1(ms) | Storage Size(M) |
| Models | Batch Size=1(ms) | Storage Size(M) |
|:--:|:--:|:--:|
| MobileNetV1_x0_25 | 3.220 | 1.900 |
| MobileNetV1_x0_5 | 9.580 | 5.200 |
......@@ -97,10 +97,9 @@ MobileNetV3是Google于2019年提出的一种基于NAS的新的轻量级网络
| ShuffleNetV2_swish | 16.023 | 9.100 |
## T4 GPU预测速度
## 基于T4 GPU的预测速度
| Models | batch_size=1,fp16(ms) | batch_size=4,fp16(ms) | batch_size=8,fp16(ms) | batch_size=1,fp32(ms) | batch_size=4,fp32(ms) | batch_size=8,fp32(ms) |
| Models | FP16<br>Batch Size=1<br>(ms) | FP16<br>Batch Size=4<br>(ms) | FP16<br>Batch Size=8<br>(ms) | FP32<br>Batch Size=1<br>(ms) | FP32<br>Batch Size=4<br>(ms) | FP32<br>Batch Size=8<br>(ms) |
|-----------------------------|-----------------------|-----------------------|-----------------------|-----------------------|-----------------------|-----------------------|
| MobileNetV1_x0_25 | 0.68422 | 1.13021 | 1.72095 | 0.67274 | 1.226 | 1.84096 |
| MobileNetV1_x0_5 | 0.69326 | 1.09027 | 1.84746 | 0.69947 | 1.43045 | 2.39353 |
......
docs/zh_CN/models/Others.md
浏览文件 @ 0e807423
......@@ -27,10 +27,10 @@ DarkNet53是YOLO作者在论文设计的用于目标检测的backbone，该网
## FP32预测速度
## 基于V100 GPU的预测速度
| Models | Crop Size | Resize Short Size | Batch Size=1<br>(ms) |
| Models | Crop Size | Resize Short Size | FP32<br>Batch Size=1<br>(ms) |
|---------------------------|-----------|-------------------|----------------------|
| AlexNet | 224 | 256 | 1.176 |
| SqueezeNet1_0 | 224 | 256 | 0.860 |
......@@ -41,3 +41,20 @@ DarkNet53是YOLO作者在论文设计的用于目标检测的backbone，该网
| VGG19 | 224 | 256 | 3.076 |
| DarkNet53 | 256 | 256 | 3.139 |
| ResNet50_ACNet<br>_deploy | 224 | 256 | 5.626 |
## 基于T4 GPU的预测速度
| Models | Crop Size | Resize Short Size | FP16<br>Batch Size=1<br>(ms) | FP16<br>Batch Size=4<br>(ms) | FP16<br>Batch Size=8<br>(ms) | FP32<br>Batch Size=1<br>(ms) | FP32<br>Batch Size=4<br>(ms) | FP32<br>Batch Size=8<br>(ms) |
|-----------------------|-----------|-------------------|------------------------------|------------------------------|------------------------------|------------------------------|------------------------------|------------------------------|
| AlexNet | 224 | 256 | 1.06447 | 1.70435 | 2.38402 | 1.44993 | 2.46696 | 3.72085 |
| SqueezeNet1_0 | 224 | 256 | 0.97162 | 2.06719 | 3.67499 | 0.96736 | 2.53221 | 4.54047 |
| SqueezeNet1_1 | 224 | 256 | 0.81378 | 1.62919 | 2.68044 | 0.76032 | 1.877 | 3.15298 |
| VGG11 | 224 | 256 | 2.24408 | 4.67794 | 7.6568 | 3.90412 | 9.51147 | 17.14168 |
| VGG13 | 224 | 256 | 2.58589 | 5.82708 | 10.03591 | 4.64684 | 12.61558 | 23.70015 |
| VGG16 | 224 | 256 | 3.13237 | 7.19257 | 12.50913 | 5.61769 | 16.40064 | 32.03939 |
| VGG19 | 224 | 256 | 3.69987 | 8.59168 | 15.07866 | 6.65221 | 20.4334 | 41.55902 |
| DarkNet53 | 256 | 256 | 3.18101 | 5.88419 | 10.14964 | 4.10829 | 12.1714 | 22.15266 |
| ResNet50_ACNet | 256 | 256 | 3.89002 | 4.58195 | 9.01095 | 5.33395 | 10.96843 | 18.70368 |
| ResNet50_ACNet_deploy | 224 | 256 | 2.6823 | 5.944 | 7.16655 | 3.49161 | 7.78374 | 13.94361 |
docs/zh_CN/models/ResNet_and_vd.md
浏览文件 @ 0e807423
......@@ -21,7 +21,7 @@ ResNet系列模型是在2015年提出的，一举在ILSVRC2015比赛中取得冠
通过上述曲线可以看出，层数越多，准确率越高，但是相应的参数量、计算量和延时都会增加。ResNet50_vd_ssld通过用更强的teacher和更多的数据，将其在ImageNet-1k上的验证集top-1精度进一步提高，达到了82.39%，刷新了ResNet50系列模型的精度。
c
## 精度、FLOPS和参数量
| Models | Top1 | Top5 | Reference<br>top1 | Reference<br>top5 | FLOPS<br>(G) | Parameters<br>(M) |
......@@ -68,7 +68,7 @@ c
## 基于T4 GPU的预测速度
| Models | Crop Size | Resize Short Size | FP16<br>batch_size=1<br>(ms) | FP16<br>batch_size=4<br>(ms) | FP16<br>batch_size=8<br>(ms) | FP32<br>batch_size=1<br>(ms) | FP32<br>batch_size=4<br>(ms) | FP32<br>batch_size=8<br>(ms) |
| Models | Crop Size | Resize Short Size | FP16<br>Batch Size=1<br>(ms) | FP16<br>Batch Size=4<br>(ms) | FP16<br>Batch Size=8<br>(ms) | FP32<br>Batch Size=1<br>(ms) | FP32<br>Batch Size=4<br>(ms) | FP32<br>Batch Size=8<br>(ms) |
|-------------------|-----------|-------------------|------------------------------|------------------------------|------------------------------|------------------------------|------------------------------|------------------------------|
| ResNet18 | 224 | 256 | 1.3568 | 2.5225 | 3.61904 | 1.45606 | 3.56305 | 6.28798 |
| ResNet18_vd | 224 | 256 | 1.39593 | 2.69063 | 3.88267 | 1.54557 | 3.85363 | 6.88121 |
......
docs/zh_CN/models/SEResNext_and_Res2Net.md
浏览文件 @ 0e807423
......@@ -84,7 +84,7 @@ Res2Net是2019年提出的一种全新的对ResNet的改进方案，该方案可
## 基于T4 GPU的预测速度
| Models | Crop Size | Resize Short Size | FP16<br>batch_size=1<br>(ms) | FP16<br>batch_size=4<br>(ms) | FP16<br>batch_size=8<br>(ms) | FP32<br>batch_size=1<br>(ms) | FP32<br>batch_size=4<br>(ms) | FP32<br>batch_size=8<br>(ms) |
| Models | Crop Size | Resize Short Size | FP16<br>Batch Size=1<br>(ms) | FP16<br>Batch Size=4<br>(ms) | FP16<br>Batch Size=8<br>(ms) | FP32<br>Batch Size=1<br>(ms) | FP32<br>Batch Size=4<br>(ms) | FP32<br>Batch Size=8<br>(ms) |
|-----------------------|-----------|-------------------|------------------------------|------------------------------|------------------------------|------------------------------|------------------------------|------------------------------|
| Res2Net50_26w_4s | 224 | 256 | 3.56067 | 6.61827 | 11.41566 | 4.47188 | 9.65722 | 17.54535 |
| Res2Net50_vd_26w_4s | 224 | 256 | 3.69221 | 6.94419 | 11.92441 | 4.52712 | 9.93247 | 18.16928 |
......
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或