mmr/tkDNN
Archived
1
0
Fork 0
Code Issues 46 Pull Requests 12 Releases 4 Activity

Fix shelfnet berkeley, update readme, minors

Browse Source 
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
This commit is contained in:
Micaela Verucchi
2021-07-20 10:57:53 +02:00
parent f137bcb694
commit b3c44a86a8
7 changed files with 29 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files
demo/demo/seg_demo.cpp
+8 -5
View File
@@ -39,7 +39,7 @@ int main(int argc, char *argv[]) {
std::string net = "shelfnet_fp32.rt";
if(argc > 1)
net = argv[1];
std::string input = "../../ShelfNet/ShelfNet18_realtime/data/leftImg8bit/test/modena/000302.png";
std::string input = "../demo/yolo_test.mp4";
if(argc > 2)
input = argv[2];
int n_batch = 1;
@@ -68,9 +68,12 @@ int main(int argc, char *argv[]) {
std::string net_name;
removePathAndExtension(net, net_name);
bool mapillary_15 = false; //TODO change me pls
if(n_classes == 15 && net_name == "shelfnet_mapillary_fp32")
mapillary_15 = true;
bool mapillary_15_colormap = false;
if( n_classes == 15 &&
( net_name == "shelfnet_mapillary_fp32" ||
net_name == "shelfnet_mapillary_fp16" ||
net_name == "shelfnet_mapillary_int8" ) )
mapillary_15_colormap = true;
//net initialization
tk::dnn::SegmentationNN segNN;
@@ -127,7 +130,7 @@ int main(int argc, char *argv[]) {
width = frame.cols;
//inference
segNN.updateOriginal(frame, true, mapillary_15);
segNN.updateOriginal(frame, true, mapillary_15_colormap);
if(show)
segNN.draw();
include/tkDNN/NetworkViz.h
+1 -1
View File
@@ -6,7 +6,7 @@
namespace tk { namespace dnn {
cv::Mat vizFloat2colorMap(cv::Mat map, double min=0, double max=0, bool mapillary_15=false);
cv::Mat vizData2Mat(dnnType *dataInput, tk::dnn::dataDim_t dim, int imgdim, double min=0, double max=0, bool mapillary_15=false);
cv::Mat vizData2Mat(dnnType *dataInput, tk::dnn::dataDim_t dim, int img_h, int img_w, double min=0, double max=0, bool mapillary_15=false);
cv::Mat vizLayer2Mat(tk::dnn::Network *net, int layer, int imgdim = 1000);
}}
include/tkDNN/SegmentationNN.h
+2 -2
View File
@@ -112,7 +112,7 @@ class SegmentationNN {
cv::Mat colored;
if(appy_colormap)
colored = vizData2Mat(tmpOutData_h, vdim, 1024, 0, classes, mapillary_15);
colored = vizData2Mat(tmpOutData_h, vdim, netRT->input_dim.h, netRT->input_dim.w, 0, classes, mapillary_15);
else{
cv::Mat colored_fp32 (cv::Size(odim.w, odim.h),CV_32FC1, tmpOutData_h);
colored_fp32.convertTo(colored, CV_8UC1);
@@ -347,7 +347,7 @@ class SegmentationNN {
cv::Mat colored;
if(apply_colormap)
colored = vizData2Mat(tmpOutData_h, vdim, 1024, 0, classes, mapillary_15);
colored = vizData2Mat(tmpOutData_h, vdim, netRT->input_dim.h, netRT->input_dim.w, 0, classes, mapillary_15);
else{
cv::Mat colored_fp32 (cv::Size(odim.w, odim.h),CV_32FC1, tmpOutData_h);
colored_fp32.convertTo(colored, CV_8UC1);
README_seg.md → readme/README_seg.md
+14 -9
View File
@@ -18,12 +18,12 @@ python export.py
## Run the demo
To run the semantic segmentation demo follow these steps (example with shelfnet_mapillary):
To run the semantic segmentation demo follow these steps (example with shelfnet):
```
rm shelfnet_mapillary_fp32.rt # be sure to delete(or move) old tensorRT files
export TKDNN_BATCHSIZE=4 # be sure you have batch size > than 1 if you want to run inference on images bigger than 1024
./test_shelfnet_mapillary # run the yolo test (is slow)
./demo shelfnet_mapillary_fp32.rt ../demo/yolo_test.mp4 1 15
rm shelfnet_fp32.rt # be sure to delete(or move) old tensorRT files
export TKDNN_BATCHSIZE=4 # be sure you have batch size > than 1 if you want to run inference on images bigger than 1024
./test_shelfnet # run the yolo test (is slow)
./demo shelfnet_fp32.rt ../demo/yolo_test.mp4 1 19
```
In general the demo program takes the following parameters:
```
@@ -37,11 +37,13 @@ where
* ```<resize-flag>``` if set to 0 the demo will not resize the input frames, but use it as it is, otherwise it will resize it.
* ```<baseline-resize>``` is ```<resize-flag>``` is set to 1, then the input frames will be proportionally resized using ```<baseline-resize>``` as width baseline.
* ```<show-flag>``` if set to 0 the demo will not show the visualization but save the video into result.mp4 (if n-batches ==1)
* ```<write-pred>``` if set to 0 (deafult) the demo will run, otherwise the evaluation of a dataset will run and the output of the segmentation will be saved. Attention: this is under development and paths are embedded, so change them in the code in advance.
* ```<write-pred>``` if set to 0 (default) the demo will run, otherwise the evaluation of a dataset will run and the output of the segmentation will be saved. Attention: this is under development and paths are embedded, so change them in the code in advance.
N.b. By default it is used FP32 inference
<!-- TODO: add gif -->
![gif](output.gif "Results on yolo_test.mp4")
## Existing tests and supported networks
@@ -49,8 +51,11 @@ N.b. By default it is used FP32 inference
| :---------------- | :-------------------------------------------- | :-----------------------------------------------------------: | :-------: | :-----------: | :------------------------------------------------------------------------ |
| shelfnet | ShelfNet18_realtime<sup>1</sup> | [Cityscapes](https://www.cityscapes-dataset.com/) | 19 | 1024x1024 | [weights](https://cloud.hipert.unimore.it/s/mEDZMRJaGCFWSJF/download) |
| shelfnet_berkeley | ShelfNet18_realtime<sup>1</sup> | [DeepDrive](https://bdd-data.berkeley.edu/) | 20 | 1024x1024 | [weights](https://cloud.hipert.unimore.it/s/m92e7QdD9gYMF7f/download) |
| shelfnet_mapillary | ShelfNet18_realtime<sup>1</sup> | [Mapillary Vistas](https://www.mapillary.com/dataset/vistas?pKey=aFWuj_m4nGoq3-tDz5KAqQ)<sup>*</sup> | 15 | 1024x1024 | [weights](https://cloud.hipert.unimore.it/s/6WnZCKLjik7xrny/download) |
1. Zhuang, Juntang, et al. "ShelfNet for fast semantic segmentation." Proceedings of the IEEE International Conference on Computer Vision Workshops. 2019.
*. Mapillary Vistas has originally 66 classes, but we reduced them to 15 to improve the results on the categories of our interest.
## Known issues
When creating the rt file all the checks returns errors. It is due to a different resize function and handling of the original ShelfNet outputs.
However, the network is supposed to work.
readme/output.gif
BIN
View File
Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 6.3 MiB

src/NetworkViz.cpp
+3 -4
View File
@@ -113,7 +113,7 @@ cv::Mat vizFloat2colorMap(cv::Mat map,double min, double max, bool mapillary_15)
return falseColorsMap;
}
cv::Mat vizData2Mat(dnnType *dataInput, tk::dnn::dataDim_t dim, int imgdim, double min, double max, bool mapillary_15) {
cv::Mat vizData2Mat(dnnType *dataInput, tk::dnn::dataDim_t dim, int img_h, int img_w, double min, double max, bool mapillary_15) {
dnnType *data = nullptr;
// copy to CPU
@@ -135,8 +135,7 @@ cv::Mat vizData2Mat(dnnType *dataInput, tk::dnn::dataDim_t dim, int imgdim, doub
raw.copyTo(grid.rowRange(r*dim.h, r*dim.h + dim.h).colRange(c*dim.w, c*dim.w + dim.w));
}
float ar = float(dim.w)/dim.h;
cv::Size vdim(ar*imgdim, imgdim);
cv::Size vdim(img_w, img_h);
cv::Mat viz;
cv::resize(grid, viz, vdim, 0, 0, 0);
@@ -150,7 +149,7 @@ cv::Mat vizData2Mat(dnnType *dataInput, tk::dnn::dataDim_t dim, int imgdim, doub
cv::Mat vizLayer2Mat(tk::dnn::Network *net, int layer, int imgdim) {
if(layer >= net->num_layers)
FatalError("Could not viz layer\n");
return vizData2Mat(net->layers[layer]->dstData, net->layers[layer]->output_dim, imgdim);
return vizData2Mat(net->layers[layer]->dstData, net->layers[layer]->output_dim, imgdim, imgdim);
//cv::imwrite("viz/layer" + std::to_string(layer) + ".png", viz);
//cv::imshow("layer", viz);
tests/shelfnet/shelfnet_mapillary.cpp
+1
View File
@@ -85,6 +85,7 @@ int main()
downloadWeightsifDoNotExist(input_bin, "shelfnet_mapillary", "https://cloud.hipert.unimore.it/s/6WnZCKLjik7xrny/download");
// Mapillary Vistas has originally 66 classes, but we reduced them to 15 to improve the results on the categories of our interest.
int classes = 15;
// Network layout