Skip to content

Commit e9c20a9

Browse files
Sam-gsjSam-gsj
authored
fix conflict (#4275)
1 parent d2ccedc commit e9c20a9

File tree

181 files changed

+13044
-10314
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

181 files changed

+13044
-10314
lines changed

‎docs/module_usage/tutorials/cv_modules/3d_bev_detection.en.md

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -17,10 +17,10 @@ The 3D multimodal fusion detection module is a key component in the fields of co
1717
<th>Introduction</th>
1818
</tr>
1919
<tr>
20-
<td>BEVFusion</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/BEVFusion_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/BEVFusion_pretrained.pdparams">Training Model</a></td>
20+
<td>BEVFusion</td>
21+
<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/BEVFusion_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/BEVFusion_pretrained.pdparams">Training Model</a></td>
2122
<td>53.9</td>
2223
<td>60.9</td>
23-
2424
<td rowspan="2">BEVFusion is a multimodal fusion model in the Bird's Eye View (BEV) perspective. It uses two branches to process data from different modalities to obtain features of lidar and camera in the BEV perspective. The camera branch uses the LSS (Lift, Splat, and Scatter) bottom-up approach to explicitly generate image BEV features, while the lidar branch uses a classic point cloud detection network. Finally, the BEV features of the two modalities are aligned and fused for application in detection heads or segmentation heads.</td>
2525
</tr>
2626
<tr>
@@ -36,7 +36,7 @@ The 3D multimodal fusion detection module is a key component in the fields of co
3636
<ul>
3737
<li>GPU: NVIDIA Tesla T4</li>
3838
<li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
39-
<li>Other Environments: Ubuntu 20.04 / cuDNN 8.6 / TensorRT 8.5.2.2</li>
39+
<li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
4040
</ul>
4141
</li>
4242
</ul>

‎docs/module_usage/tutorials/cv_modules/3d_bev_detection.md

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -17,10 +17,10 @@ comments: true
1717
<th>介绍</th>
1818
</tr>
1919
<tr>
20-
<td>BEVFusion</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/BEVFusion_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/BEVFusion_pretrained.pdparams">训练模型</a></td>
20+
<td>BEVFusion</td>
21+
<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/BEVFusion_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/BEVFusion_pretrained.pdparams">训练模型</a></td>
2122
<td>53.9</td>
2223
<td>60.9</td>
23-
2424
<td rowspan="2">BEVFusion是一种在BEV视角下的多模态融合模型，采用两个分支处理不同模态的数据，得到lidar和camera在BEV视角下的特征，camera分支采用LSS这种自底向上的方式来显式的生成图像BEV特征，lidar分支采用经典的点云检测网络，最后对两种模态的BEV特征进行对齐和融合，应用于检测head或分割head
2525

2626
</td>
@@ -40,7 +40,7 @@ comments: true
4040
<ul>
4141
<li>GPU：NVIDIA Tesla T4</li>
4242
<li>CPU：Intel Xeon Gold 6271C @ 2.60GHz</li>
43-
<li>其他环境：Ubuntu 20.04 / cuDNN 8.6 / TensorRT 8.5.2.2</li>
43+
<li>其他环境：Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
4444
</ul>
4545
</li>
4646
</ul>

‎docs/module_usage/tutorials/cv_modules/anomaly_detection.en.md

Lines changed: 4 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -15,13 +15,14 @@ Unsupervised anomaly detection is a technology that automatically identifies and
1515
<tr>
1616
<th>Model</th><th>Model Download Link</th>
1717
<th>ROCAUC（Avg）</th>
18-
<th>Model Size (M)</th>
18+
<th>Model Storage Size (MB)</th>
1919
<th>Description</th>
2020
</tr>
2121
</thead>
2222
<tbody>
2323
<tr>
24-
<td>STFPM</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/STFPM_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/STFPM_pretrained.pdparams">Training Model</a></td>
24+
<td>STFPM</td>
25+
<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/STFPM_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/STFPM_pretrained.pdparams">Training Model</a></td>
2526
<td>0.962</td>
2627
<td>22.5</td>
2728
<td>An unsupervised anomaly detection algorithm based on representation consists of a pre-trained teacher network and a student network with the same structure. The student network detects anomalies by matching its own features with the corresponding features in the teacher network.</td>
@@ -38,7 +39,7 @@ Unsupervised anomaly detection is a technology that automatically identifies and
3839
<ul>
3940
<li>GPU: NVIDIA Tesla T4</li>
4041
<li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
41-
<li>Other Environments: Ubuntu 20.04 / cuDNN 8.6 / TensorRT 8.5.2.2</li>
42+
<li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
4243
</ul>
4344
</li>
4445
</ul>

‎docs/module_usage/tutorials/cv_modules/anomaly_detection.md

Lines changed: 4 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -15,13 +15,14 @@ comments: true
1515
<tr>
1616
<th>模型</th><th>模型下载链接</th>
1717
<th>mIoU</th>
18-
<th>模型存储大小（M)</th>
18+
<th>模型存储大小（MB）</th>
1919
<th>介绍</th>
2020
</tr>
2121
</thead>
2222
<tbody>
2323
<tr>
24-
<td>STFPM</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/STFPM_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/STFPM_pretrained.pdparams">训练模型</a></td>
24+
<td>STFPM</td>
25+
<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/STFPM_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/STFPM_pretrained.pdparams">训练模型</a></td>
2526
<td>0.9901</td>
2627
<td>22.5</td>
2728
<td>一种基于表示的图像异常检测算法，由预训练的教师网络和结构相同的学生网络组成。学生网络通过将自身特征与教师网络中的对应特征相匹配来检测异常。</td>
@@ -39,7 +40,7 @@ comments: true
3940
<ul>
4041
<li>GPU：NVIDIA Tesla T4</li>
4142
<li>CPU：Intel Xeon Gold 6271C @ 2.60GHz</li>
42-
<li>其他环境：Ubuntu 20.04 / cuDNN 8.6 / TensorRT 8.5.2.2</li>
43+
<li>其他环境：Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
4344
</ul>
4445
</li>
4546
</ul>

‎docs/module_usage/tutorials/cv_modules/face_detection.en.md

Lines changed: 17 additions & 13 deletions
Original file line numberDiff line numberDiff line change
@@ -23,34 +23,38 @@ Face detection is a fundamental task in object detection, aiming to automaticall
2323
</thead>
2424
<tbody>
2525
<tr>
26-
<td style="text-align: center;">BlazeFace</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/BlazeFace_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/BlazeFace_pretrained.pdparams">Training Model</a></td>
26+
<td style="text-align: center;">BlazeFace</td>
27+
<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/BlazeFace_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/BlazeFace_pretrained.pdparams">Training Model</a></td>
2728
<td style="text-align: center;">77.7/73.4/49.5</td>
28-
<td style="text-align: center;">60.34 / 54.76</td>
29-
<td style="text-align: center;">84.18 / 84.18</td>
29+
<td style="text-align: center;">50.90 / 45.74</td>
30+
<td style="text-align: center;">71.92 / 71.92</td>
3031
<td style="text-align: center;">0.447</td>
3132
<td style="text-align: center;">A lightweight and efficient face detection model</td>
3233
</tr>
3334
<tr>
34-
<td style="text-align: center;">BlazeFace-FPN-SSH</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/BlazeFace-FPN-SSH_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/BlazeFace-FPN-SSH_pretrained.pdparams">Training Model</a></td>
35+
<td style="text-align: center;">BlazeFace-FPN-SSH</td>
36+
<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/BlazeFace-FPN-SSH_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/BlazeFace-FPN-SSH_pretrained.pdparams">Training Model</a></td>
3537
<td style="text-align: center;">83.2/80.5/60.5</td>
36-
<td style="text-align: center;">69.29 / 63.42</td>
37-
<td style="text-align: center;">86.96 / 86.96</td>
38+
<td style="text-align: center;">58.99 / 51.75</td>
39+
<td style="text-align: center;">87.39 / 87.39</td>
3840
<td style="text-align: center;">0.606</td>
3941
<td style="text-align: center;">An improved model of BlazeFace, incorporating FPN and SSH structures</td>
4042
</tr>
4143
<tr>
42-
<td style="text-align: center;">PicoDet_LCNet_x2_5_face</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PicoDet_LCNet_x2_5_face_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet_LCNet_x2_5_face_pretrained.pdparams">Training Model</a></td>
44+
<td style="text-align: center;">PicoDet_LCNet_x2_5_face</td>
45+
<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PicoDet_LCNet_x2_5_face_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet_LCNet_x2_5_face_pretrained.pdparams">Training Model</a></td>
4346
<td style="text-align: center;">93.7/90.7/68.1</td>
44-
<td style="text-align: center;">35.37 / 12.88</td>
45-
<td style="text-align: center;">126.24 / 126.24</td>
47+
<td style="text-align: center;">33.91 / 26.53</td>
48+
<td style="text-align: center;">153.56 / 79.21</td>
4649
<td style="text-align: center;">28.9</td>
4750
<td style="text-align: center;">Face Detection model based on PicoDet_LCNet_x2_5</td>
4851
</tr>
4952
<tr>
50-
<td style="text-align: center;">PP-YOLOE_plus-S_face</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-YOLOE_plus-S_face_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-YOLOE_plus-S_face_pretrained.pdparams">Training Model</a></td>
53+
<td style="text-align: center;">PP-YOLOE_plus-S_face</td>
54+
<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-YOLOE_plus-S_face_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-YOLOE_plus-S_face_pretrained.pdparams">Training Model</a></td>
5155
<td style="text-align: center;">93.9/91.8/79.8</td>
52-
<td style="text-align: center;">22.54 / 8.33</td>
53-
<td style="text-align: center;">138.67 / 138.67</td>
56+
<td style="text-align: center;">21.28 / 11.09</td>
57+
<td style="text-align: center;">137.26 / 72.09</td>
5458
<td style="text-align: center;">26.5</td>
5559
<td style="text-align: center;">Face Detection model based on PP-YOLOE_plus-S</td>
5660
</tr>
@@ -67,7 +71,7 @@ Face detection is a fundamental task in object detection, aiming to automaticall
6771
<ul>
6872
<li>GPU: NVIDIA Tesla T4</li>
6973
<li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
70-
<li>Other Environments: Ubuntu 20.04 / cuDNN 8.6 / TensorRT 8.5.2.2</li>
74+
<li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
7175
</ul>
7276
</li>
7377
</ul>

‎docs/module_usage/tutorials/cv_modules/face_detection.md

Lines changed: 18 additions & 14 deletions
Original file line numberDiff line numberDiff line change
@@ -16,40 +16,44 @@ comments: true
1616
<th>AP(%)</th>
1717
<th>GPU推理耗时（ms）<br/>[常规模式 / 高性能模式]</th>
1818
<th>CPU推理耗时（ms）<br/>[常规模式 / 高性能模式]</th>
19-
<th>模型存储大小 (M)</th>
19+
<th>模型存储大小（MB）</th>
2020
<th>介绍</th>
2121
</tr>
2222
</thead>
2323
<tbody>
2424
<tr>
25-
<td>BlazeFace</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/BlazeFace_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/BlazeFace_pretrained.pdparams">训练模型</a></td>
25+
<td>BlazeFace</td>
26+
<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/BlazeFace_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/BlazeFace_pretrained.pdparams">训练模型</a></td>
2627
<td>15.4</td>
27-
<td>60.34 / 54.76</td>
28-
<td>84.18 / 84.18</td>
28+
<td>50.90 / 45.74</td>
29+
<td>71.92 / 71.92</td>
2930
<td>0.447</td>
3031
<td>轻量高效的人脸检测模型</td>
3132
</tr>
3233
<tr>
33-
<td>BlazeFace-FPN-SSH</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/BlazeFace-FPN-SSH_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/BlazeFace-FPN-SSH_pretrained.pdparams">训练模型</a></td>
34+
<td>BlazeFace-FPN-SSH</td>
35+
<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/BlazeFace-FPN-SSH_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/BlazeFace-FPN-SSH_pretrained.pdparams">训练模型</a></td>
3436
<td>18.7</td>
35-
<td>69.29 / 63.42</td>
36-
<td>86.96 / 86.96</td>
37+
<td>58.99 / 51.75</td>
38+
<td>87.39 / 87.39</td>
3739
<td>0.606</td>
3840
<td>BlazeFace的改进模型，增加FPN和SSH结构</td>
3941
</tr>
4042
<tr>
41-
<td>PicoDet_LCNet_x2_5_face</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PicoDet_LCNet_x2_5_face_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet_LCNet_x2_5_face_pretrained.pdparams">训练模型</a></td>
43+
<td>PicoDet_LCNet_x2_5_face</td>
44+
<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PicoDet_LCNet_x2_5_face_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PicoDet_LCNet_x2_5_face_pretrained.pdparams">训练模型</a></td>
4245
<td>31.4</td>
43-
<td>35.37 / 12.88</td>
44-
<td>126.24 / 126.24</td>
46+
<td>33.91 / 26.53</td>
47+
<td>153.56 / 79.21</td>
4548
<td>28.9</td>
4649
<td>基于PicoDet_LCNet_x2_5的人脸检测模型</td>
4750
</tr>
4851
<tr>
49-
<td>PP-YOLOE_plus-S_face</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-YOLOE_plus-S_face_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-YOLOE_plus-S_face_pretrained.pdparams">训练模型</a></td>
52+
<td>PP-YOLOE_plus-S_face</td>
53+
<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-YOLOE_plus-S_face_infer.tar">推理模型</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-YOLOE_plus-S_face_pretrained.pdparams">训练模型</a></td>
5054
<td>36.1</td>
51-
<td>22.54 / 8.33</td>
52-
<td>138.67 / 138.67</td>
55+
<td>21.28 / 11.09</td>
56+
<td>137.26 / 72.09</td>
5357
<td>26.5</td>
5458
<td>基于PP-YOLOE_plus-S的人脸检测模型</td>
5559
</tr>
@@ -66,7 +70,7 @@ comments: true
6670
<ul>
6771
<li>GPU：NVIDIA Tesla T4</li>
6872
<li>CPU：Intel Xeon Gold 6271C @ 2.60GHz</li>
69-
<li>其他环境：Ubuntu 20.04 / cuDNN 8.6 / TensorRT 8.5.2.2</li>
73+
<li>其他环境：Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
7074
</ul>
7175
</li>
7276
</ul>

‎docs/module_usage/tutorials/cv_modules/face_feature.en.md

Lines changed: 10 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -17,26 +17,28 @@ Face feature models typically take standardized face images processed through de
1717
<th>Acc (%)<br/>AgeDB-30/CFP-FP/LFW</th>
1818
<th>GPU Inference Time (ms)<br/>[Normal Mode / High-Performance Mode]</th>
1919
<th>CPU Inference Time (ms)<br/>[Normal Mode / High-Performance Mode]</th>
20-
<th>Model Size (M)</th>
20+
<th>Model Storage Size (MB)</th>
2121
<th>Description</th>
2222
</tr>
2323
</thead>
2424
<tbody>
2525
<tr>
26-
<td>MobileFaceNet</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/MobileFaceNet_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/MobileFaceNet_pretrained.pdparams">Training Model</a></td>
26+
<td>MobileFaceNet</td>
27+
<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/MobileFaceNet_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/MobileFaceNet_pretrained.pdparams">Training Model</a></td>
2728
<td>128</td>
2829
<td>96.28/96.71/99.58</td>
29-
<td>3.16 / 0.48</td>
30-
<td>6.49 / 6.49</td>
30+
<td>3.31 / 0.73</td>
31+
<td>5.93 / 1.30</td>
3132
<td>4.1</td>
3233
<td>Face feature model trained on MobileFaceNet with MS1Mv3 dataset</td>
3334
</tr>
3435
<tr>
35-
<td>ResNet50_face</td><td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/ResNet50_face_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ResNet50_face_pretrained.pdparams">Training Model</a></td>
36+
<td>ResNet50_face</td>
37+
<td><a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/ResNet50_face_infer.tar">Inference Model</a>/<a href="https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/ResNet50_face_pretrained.pdparams">Training Model</a></td>
3638
<td>512</td>
3739
<td>98.12/98.56/99.77</td>
38-
<td>5.68 / 1.09</td>
39-
<td>14.96 / 11.90</td>
40+
<td>6.12 / 3.11</td>
41+
<td>15.85 / 9.44</td>
4042
<td>87.2</td>
4143
<td>Face feature model trained on ResNet50 with MS1Mv3 dataset</td>
4244
</tr>
@@ -53,7 +55,7 @@ Face feature models typically take standardized face images processed through de
5355
<ul>
5456
<li>GPU: NVIDIA Tesla T4</li>
5557
<li>CPU: Intel Xeon Gold 6271C @ 2.60GHz</li>
56-
<li>Other Environments: Ubuntu 20.04 / cuDNN 8.6 / TensorRT 8.5.2.2</li>
58+
<li>Other Environments: Ubuntu 20.04 / CUDA 11.8 / cuDNN 8.9 / TensorRT 8.6.1.6</li>
5759
</ul>
5860
</li>
5961
</ul>

0 commit comments

Comments
 (0)