Skip to content

Commit 4ccef0e

Browse files
authored
Remove "evolving"
1 parent b444b15 commit 4ccef0e

File tree

1 file changed

+4
-4
lines changed

1 file changed

+4
-4
lines changed

README.md

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -76,7 +76,7 @@ you can use darknet2pytorch to convert it yourself, or download my converted mod
7676
python train.py -g [GPU_ID] -dir [Dataset direction] ...
7777
```
7878
79-
# 2. Inference (Evolving)
79+
# 2. Inference
8080
8181
## 2.1 Performance on MS COCO dataset (using pretrained DarknetWeights from <https://github.com/AlexeyAB/darknet>)
8282
@@ -140,7 +140,7 @@ There are 2 inference outputs.
140140
Until now, still a small piece of post-processing including NMS is required. We are trying to minimize time and complexity of post-processing.
141141

142142

143-
# 3. Darknet2ONNX (Evolving)
143+
# 3. Darknet2ONNX
144144

145145
- **This script is to convert the official pretrained darknet model into ONNX**
146146

@@ -167,7 +167,7 @@ Until now, still a small piece of post-processing including NMS is required. We
167167
- Dynamic batch size will generate only one ONNX model
168168
- Static batch size will generate 2 ONNX models, one is for running the demo (batch_size=1)
169169

170-
# 4. Pytorch2ONNX (Evolving)
170+
# 4. Pytorch2ONNX
171171

172172
- **You can convert your trained pytorch model into ONNX using this script**
173173

@@ -201,7 +201,7 @@ Until now, still a small piece of post-processing including NMS is required. We
201201
- Static batch size will generate 2 ONNX models, one is for running the demo (batch_size=1)
202202

203203

204-
# 5. ONNX2TensorRT (Evolving)
204+
# 5. ONNX2TensorRT
205205

206206
- **TensorRT version Recommended: 7.0, 7.1**
207207

0 commit comments

Comments
 (0)