summaryrefslogtreecommitdiff
path: root/README.md
diff options
context:
space:
mode:
Diffstat (limited to 'README.md')
-rw-r--r--README.md6
1 files changed, 6 insertions, 0 deletions
diff --git a/README.md b/README.md
index 9b236aa..98bd0bc 100644
--- a/README.md
+++ b/README.md
@@ -38,12 +38,18 @@ cd Data
./shanghaitech.sh
```
+If the download shell does not work (I guess the download link in shell script is not permanent), please manually download all datasets from [ped1.tar.gz, ped2.tar.gz, avenue.tar.gz and shanghaitech.tar.gz](https://onedrive.live.com/?authkey=%21AMqh2fTSemfrokE&id=3705E349C336415F%215109&cid=3705E349C336415F)
+and tar each tar.gz file, and move them in to **Data** folder.
+
## 3. Testing on saved models
* Download the trained models (There are the pretrained FlowNet and the trained models of the papers, such as ped1, ped2 and avenue).
```shell
cd checkpoints
./download_pretrains.sh
```
+If the download shell does not work (I guess the download link in shell script is not permanent), please manually download pretrained models from [pretrains.tar.gz](https://onedrive.live.com/?authkey=%21AMqh2fTSemfrokE&id=3705E349C336415F%215109&cid=3705E349C336415F)
+and tar -xvf pretrains.tar.gz, and move pretrains into **Codes/checkpoints** folder.
+
* Running the sript (as ped2 and avenue datasets for examples) and cd into **Codes** folder at first.
```shell
python inference.py --dataset ped2 \