update dnmetis/README.md.
This commit is contained in:
+13
-7
@@ -6,13 +6,19 @@ pip3.7.5 setup.py install
|
|||||||
```
|
```
|
||||||
Details of dnmetis_backend installation can be found in backend_C++/dnmetis_backend/README.md. Notice that, you just need to install requirements once for a brand new Ai1-Inference environment。
|
Details of dnmetis_backend installation can be found in backend_C++/dnmetis_backend/README.md. Notice that, you just need to install requirements once for a brand new Ai1-Inference environment。
|
||||||
|
|
||||||
## 2.Download dataset and model(.om)
|
## 2.Download model(.om)
|
||||||
|
|
||||||
1.download Imagenet-val dataset URL: http://www.image-net.org/download-imageurls
|
1.download efficientnet-b8 model(.om) URL:
|
||||||
|
```
|
||||||
2.download efficientnet-b8 model(.om) URL: obs://hwwheel23/efficientnet-b8.om
|
链接:https://pan.baidu.com/s/1N-kpQoDe3NRxvjFKjAT9AA
|
||||||
|
提取码:tvg0
|
||||||
3.process the original Imagenet-val dataset as list:
|
```
|
||||||
|
Original efficientnet-b8 pb model URL:
|
||||||
|
```
|
||||||
|
链接:https://pan.baidu.com/s/1CajdSlNTh6k35RoyOn-3Ug
|
||||||
|
提取码:slqm
|
||||||
|
```
|
||||||
|
2.Imagenet-val dataset and labels in val_map.txt:
|
||||||
|
|
||||||

|

|
||||||
|
|
||||||
@@ -24,7 +30,7 @@ sh run_efficientnet-b8.sh
|
|||||||
|
|
||||||
or
|
or
|
||||||
|
|
||||||
python3.7 main.py --model=/data/hwwheel123/model/efficientnet-b8.om --image_size='672,672,3' --inputs='images:0' --outputs='Softmax:0' --precision=fp16
|
python3.7 main.py --model=./model/efficientnet-b8.om --image_size='672,672,3' --inputs='images:0' --outputs='Softmax:0' --precision=fp16
|
||||||
|
|
||||||
|
|
||||||
## 4.ATC offline model generate (optional):
|
## 4.ATC offline model generate (optional):
|
||||||
|
|||||||
Reference in New Issue
Block a user