File tree 1 file changed +4
-4
lines changed
1 file changed +4
-4
lines changed Original file line number Diff line number Diff line change @@ -76,7 +76,7 @@ you can use darknet2pytorch to convert it yourself, or download my converted mod
76
76
python train.py -g [GPU_ID] -dir [Dataset direction] ...
77
77
```
78
78
79
- # 2. Inference (Evolving)
79
+ # 2. Inference
80
80
81
81
## 2.1 Performance on MS COCO dataset (using pretrained DarknetWeights from <https://github.com/AlexeyAB/darknet>)
82
82
@@ -140,7 +140,7 @@ There are 2 inference outputs.
140
140
Until now, still a small piece of post-processing including NMS is required. We are trying to minimize time and complexity of post-processing.
141
141
142
142
143
- # 3. Darknet2ONNX (Evolving)
143
+ # 3. Darknet2ONNX
144
144
145
145
- ** This script is to convert the official pretrained darknet model into ONNX**
146
146
@@ -167,7 +167,7 @@ Until now, still a small piece of post-processing including NMS is required. We
167
167
- Dynamic batch size will generate only one ONNX model
168
168
- Static batch size will generate 2 ONNX models, one is for running the demo (batch_size=1)
169
169
170
- # 4. Pytorch2ONNX (Evolving)
170
+ # 4. Pytorch2ONNX
171
171
172
172
- ** You can convert your trained pytorch model into ONNX using this script**
173
173
@@ -201,7 +201,7 @@ Until now, still a small piece of post-processing including NMS is required. We
201
201
- Static batch size will generate 2 ONNX models, one is for running the demo (batch_size=1)
202
202
203
203
204
- # 5. ONNX2TensorRT (Evolving)
204
+ # 5. ONNX2TensorRT
205
205
206
206
- ** TensorRT version Recommended: 7.0, 7.1**
207
207
You can’t perform that action at this time.
0 commit comments