README.md 23.9 KB
Newer Older
Francesco Gatti's avatar
README  
Francesco Gatti committed
1
# tkDNN
Micaela Verucchi's avatar
Micaela Verucchi committed
2
tkDNN is a Deep Neural Network library built with cuDNN and tensorRT primitives, specifically thought to work on NVIDIA Jetson Boards. It has been tested on TK1(branch cudnn2), TX1, TX2, AGX Xavier, Nano and several discrete GPUs.
Micaela Verucchi's avatar
Micaela Verucchi committed
3
The main goal of this project is to exploit NVIDIA boards as much as possible to obtain the best inference performance. It does not allow training. 
Francesco Gatti's avatar
README  
Francesco Gatti committed
4

Micaela Verucchi's avatar
Micaela Verucchi committed
5

Micaela Verucchi's avatar
Micaela Verucchi committed
6
If you use tkDNN in your research, please cite the [following paper](https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9212130&casa_token=sQTJXi7tJNoAAAAA:BguH9xCIY48MxbtDS3LXzIXzO-9sWArm7Hd7y7BwaLmqRuM_Gx8bOYizFPNMNtpo5K0kB-P-). For use in commercial solutions, write at gattifrancesco@hotmail.it and micaela.verucchi@unimore.it or refer to https://hipert.unimore.it/ .
Micaela Verucchi's avatar
Micaela Verucchi committed
7
8

```
Micaela Verucchi's avatar
Micaela Verucchi committed
9
10
11
12
13
14
15
16
17
@inproceedings{verucchi2020systematic,
  title={A Systematic Assessment of Embedded Neural Networks for Object Detection},
  author={Verucchi, Micaela and Brilli, Gianluca and Sapienza, Davide and Verasani, Mattia and Arena, Marco and Gatti, Francesco and Capotondi, Alessandro and Cavicchioli, Roberto and Bertogna, Marko and Solieri, Marco},
  booktitle={2020 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)},
  volume={1},
  pages={937--944},
  year={2020},
  organization={IEEE}
}
Micaela Verucchi's avatar
Micaela Verucchi committed
18
19
```

Micaela Verucchi's avatar
Micaela Verucchi committed
20
## FPS Results
micaela's avatar
micaela committed
21
Inference FPS of yolov4 with tkDNN, average of 1200 images with the same dimension as the input size, on 
Micaela Verucchi's avatar
Micaela Verucchi committed
22
23
  * RTX 2080Ti (CUDA 10.2, TensorRT 7.0.0, Cudnn 7.6.5);
  * Xavier AGX, Jetpack 4.3 (CUDA 10.0, CUDNN 7.6.3, tensorrt 6.0.1 );
24
  * Xavier NX, Jetpack 4.4  (CUDA 10.2, CUDNN 8.0.0, tensorrt 7.1.0 ). 
Micaela Verucchi's avatar
Micaela Verucchi committed
25
26
27
28
29
  * Tx2, Jetpack 4.2 (CUDA 10.0, CUDNN 7.3.1, tensorrt 5.0.6 );
  * Jetson Nano, Jetpack 4.4  (CUDA 10.2, CUDNN 8.0.0, tensorrt 7.1.0 ). 

| Platform   | Network    | FP32, B=1 | FP32, B=4	| FP16, B=1 |	FP16, B=4 |	INT8, B=1 |	INT8, B=4 | 
| :------:   | :-----:    | :-----:   | :-----:   | :-----:   |	:-----:   |	:-----:   |	:-----:   | 
30
31
32
33
34
35
36
37
| RTX 2080Ti | yolo4 320  | 118.59	  | 237.31	  | 207.81	  | 443.32	  | 262.37	  | 530.93    | 
| RTX 2080Ti | yolo4 416  | 104.81	  | 162.86	  | 169.06	  | 293.78	  | 206.93	  | 353.26    | 
| RTX 2080Ti | yolo4 512  | 92.98	    | 132.43	  | 140.36	  | 215.17	  | 165.35	  | 254.96    | 
| RTX 2080Ti | yolo4 608  | 63.77	    | 81.53	    | 111.39	  | 152.89	  | 127.79	  | 184.72    | 
| AGX Xavier | yolo4 320  |	26.78	    | 32.05	    | 57.14	    | 79.05	    | 73.15	    | 97.56     |
| AGX Xavier | yolo4 416  |	19.96	    | 21.52	    | 41.01	    | 49.00	    | 50.81	    | 60.61     |
| AGX Xavier | yolo4 512  |	16.58	    | 16.98	    | 31.12	    | 33.84	    | 37.82	    | 41.28     |
| AGX Xavier | yolo4 608  |	9.45 	    | 10.13	    | 21.92	    | 23.36	    | 27.05	    | 28.93     |
38
39
40
41
| Xavier NX  | yolo4 320  |	14.56	    | 16.25	    | 30.14	    | 41.15	    | 42.13	    | 53.42     |
| Xavier NX  | yolo4 416  |	10.02	    | 10.60	    | 22.43	    | 25.59	    | 29.08	    | 32.94     |
| Xavier NX  | yolo4 512  |	8.10	    | 8.32	    | 15.78	    | 17.13	    | 20.51	    | 22.46     |
| Xavier NX  | yolo4 608  |	5.26	    | 5.18	    | 11.54	    | 12.06	    | 15.09	    | 15.82     |
42
43
44
45
46
47
48
49
| Tx2        | yolo4 320	| 11.18	    | 12.07	    | 15.32	    | 16.31     | -         | -         |
| Tx2        | yolo4 416	| 7.30	    | 7.58	    | 9.45	    | 9.90      | -         | -         |
| Tx2        | yolo4 512	| 5.96	    | 5.95	    | 7.22	    | 7.23      | -         | -         |
| Tx2        | yolo4 608	| 3.63	    | 3.65	    | 4.67	    | 4.70      | -         | -         |
| Nano       | yolo4 320	| 4.23	    | 4.55	    | 6.14	    | 6.53      | -         | -         |
| Nano       | yolo4 416	| 2.88	    | 3.00	    | 3.90	    | 4.04      | -         | -         |
| Nano       | yolo4 512	| 2.32	    | 2.34	    | 3.02	    | 3.04      | -         | -         |
| Nano       | yolo4 608	| 1.40	    | 1.41	    | 1.92	    | 1.93      | -         | -         |
Micaela Verucchi's avatar
Micaela Verucchi committed
50

Micaela Verucchi's avatar
Micaela Verucchi committed
51
52
53
54
55
56
57
58
59
60
61
62
63
64
## MAP Results
Results for COCO val 2017 (5k images), on RTX 2080Ti, with conf threshold=0.001

|                      | CodaLab       | CodaLab   | CodaLab       | CodaLab     | tkDNN map     | tkDNN map |
| -------------------- | :-----------: | :-------: | :-----------: | :---------: | :-----------: | :-------: |
|                      | **tkDNN**     | **tkDNN** | **darknet**   | **darknet** | **tkDNN**     | **tkDNN** |
|                      | MAP(0.5:0.95) | AP50      | MAP(0.5:0.95) | AP50        | MAP(0.5:0.95) | AP50      |
| Yolov3 (416x416)     | 0.381         | 0.675     | 0.380         | 0.675       | 0.372         | 0.663     |
| yolov4 (416x416)     | 0.468         | 0.705     | 0.471         | 0.710       | 0.459         | 0.695     |
| yolov3tiny (416x416) | 0.096         | 0.202     | 0.096         | 0.201       | 0.093         | 0.198     |
| yolov4tiny (416x416) | 0.202         | 0.400     | 0.201         | 0.400       | 0.197         | 0.395     |
| Cnet-dla34 (512x512) | 0.366         | 0.543     | \-            | \-          | 0.361         | 0.535     |
| mv2SSD (512x512)     | 0.226         | 0.381     | \-            | \-          | 0.223         | 0.378     |

Micaela Verucchi's avatar
Micaela Verucchi committed
65
## Index
Francesco Gatti's avatar
Francesco Gatti committed
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
- [tkDNN](#tkdnn)
  - [Index](#index)
  - [Dependencies](#dependencies)
  - [About OpenCV](#about-opencv)
  - [How to compile this repo](#how-to-compile-this-repo)
  - [Workflow](#workflow)
  - [How to export weights](#how-to-export-weights)
    - [1)Export weights from darknet](#1export-weights-from-darknet)
    - [2)Export weights for DLA34 and ResNet101](#2export-weights-for-dla34-and-resnet101)
    - [3)Export weights for CenterNet](#3export-weights-for-centernet)
    - [4)Export weights for MobileNetSSD](#4export-weights-for-mobilenetssd)
  - [Run the demo](#run-the-demo)
    - [FP16 inference](#fp16-inference)
    - [INT8 inference](#int8-inference)
  - [mAP demo](#map-demo)
  - [Existing tests and supported networks](#existing-tests-and-supported-networks)
  - [References](#references)
Micaela Verucchi's avatar
Micaela Verucchi committed
83
84
85
86
87
88




## Dependencies
This branch works on every NVIDIA GPU that supports the dependencies:
89
90
91
* CUDA 10.0
* CUDNN 7.603
* TENSORRT 6.01
92
* OPENCV 3.4
93
* yaml-cpp 0.5.2 (sudo apt install libyaml-cpp-dev)
Francesco Gatti's avatar
README  
Francesco Gatti committed
94

95
96
97
## About OpenCV
To compile and install OpenCV4 with contrib us the script ```install_OpenCV4.sh```. It will download and compile OpenCV in Download folder.
```
Micaela Verucchi's avatar
Micaela Verucchi committed
98
bash scripts/install_OpenCV4.sh
99
100
101
```
When using openCV not compiled with contrib, comment the definition of OPENCV_CUDACONTRIBCONTRIB in include/tkDNN/DetectionNN.h. When commented, the preprocessing of the networks is computed on the CPU, otherwise on the GPU. In the latter case some milliseconds are saved in the end-to-end latency. 

Micaela Verucchi's avatar
Micaela Verucchi committed
102
## How to compile this repo
Francesco Gatti's avatar
Francesco Gatti committed
103
Build with cmake. If using Ubuntu 18.04 a new version of cmake is needed (3.15 or above). 
Francesco Gatti's avatar
README  
Francesco Gatti committed
104
```
Micaela Verucchi's avatar
Micaela Verucchi committed
105
git clone https://github.com/ceccocats/tkDNN
106
cd tkDNN
Francesco Gatti's avatar
README  
Francesco Gatti committed
107
108
mkdir build
cd build
Francesco Gatti's avatar
Francesco Gatti committed
109
cmake .. 
Francesco Gatti's avatar
README  
Francesco Gatti committed
110
111
112
make
```

Micaela Verucchi's avatar
Micaela Verucchi committed
113
114
## Workflow
Steps needed to do inference on tkDNN with a custom neural network. 
Micaela Verucchi's avatar
Micaela Verucchi committed
115
* Build and train a NN model with your favorite framework.
Micaela Verucchi's avatar
Micaela Verucchi committed
116
117
118
119
* Export weights and bias for each layer and save them in a binary file (one for layer).
* Export outputs for each layer and save them in a binary file (one for layer).
* Create a new test and define the network, layer by layer using the weights extracted and the output to check the results. 
* Do inference.
Davide Sapienza's avatar
Davide Sapienza committed
120

Micaela Verucchi's avatar
Micaela Verucchi committed
121
122
## How to export weights

123
Weights are essential for any network to run inference. For each test a folder organized as follow is needed (in the build folder):
Davide Sapienza's avatar
Davide Sapienza committed
124
```
Micaela Verucchi's avatar
Micaela Verucchi committed
125
126
127
    test_nn
        |---- layers/ (folder containing a binary file for each layer with the corresponding wieghts and bias)
        |---- debug/  (folder containing a binary file for each layer with the corresponding outputs)
Davide Sapienza's avatar
Davide Sapienza committed
128
```
Micaela Verucchi's avatar
Micaela Verucchi committed
129
Therefore, once the weights have been exported, the folders layers and debug should be placed in the corresponding test.
Davide Sapienza's avatar
Davide Sapienza committed
130

Micaela Verucchi's avatar
Micaela Verucchi committed
131
### 1)Export weights from darknet
Francesco Gatti's avatar
Francesco Gatti committed
132
To export weights for NNs that are defined in darknet framework, use [this](https://git.hipert.unimore.it/fgatti/darknet.git) fork of darknet and follow these steps to obtain a correct debug and layers folder, ready for tkDNN.
Davide Sapienza's avatar
Davide Sapienza committed
133
134

```
Francesco Gatti's avatar
Francesco Gatti committed
135
git clone https://git.hipert.unimore.it/fgatti/darknet.git
136
cd darknet
Micaela Verucchi's avatar
Micaela Verucchi committed
137
138
139
make
mkdir layers debug
./darknet export <path-to-cfg-file> <path-to-weights> layers
Davide Sapienza's avatar
Davide Sapienza committed
140
```
Micaela Verucchi's avatar
Micaela Verucchi committed
141
N.b. Use compilation with CPU (leave GPU=0 in Makefile) if you also want debug. 
Davide Sapienza's avatar
Davide Sapienza committed
142

Micaela Verucchi's avatar
Micaela Verucchi committed
143
144
### 2)Export weights for DLA34 and ResNet101 
To get weights and outputs needed to run the tests dla34 and resnet101 use the Python script and the Anaconda environment included in the repository.   
Davide Sapienza's avatar
Davide Sapienza committed
145

Micaela Verucchi's avatar
Micaela Verucchi committed
146
Create Anaconda environment and activate it:
Francesco Gatti's avatar
Francesco Gatti committed
147
```
Micaela Verucchi's avatar
Micaela Verucchi committed
148
149
150
conda env create -f file_name.yml
source activate env_name
python <script name>
Francesco Gatti's avatar
Francesco Gatti committed
151
```
Micaela Verucchi's avatar
Micaela Verucchi committed
152
153
### 3)Export weights for CenterNet
To get the weights needed to run Centernet tests use [this](https://github.com/sapienzadavide/CenterNet.git) fork of the original Centernet. 
Francesco Gatti's avatar
Francesco Gatti committed
154
```
Micaela Verucchi's avatar
Micaela Verucchi committed
155
git clone https://github.com/sapienzadavide/CenterNet.git
Francesco Gatti's avatar
Francesco Gatti committed
156
```
Micaela Verucchi's avatar
Micaela Verucchi committed
157
* follow the instruction in the README.md and INSTALL.md
Davide Sapienza's avatar
Davide Sapienza committed
158
159

```
Micaela Verucchi's avatar
Micaela Verucchi committed
160
161
python demo.py --input_res 512 --arch resdcn_101 ctdet --demo /path/to/image/or/folder/or/video/or/webcam --load_model ../models/ctdet_coco_resdcn101.pth --exp_wo --exp_wo_dim 512
python demo.py --input_res 512 --arch dla_34 ctdet --demo /path/to/image/or/folder/or/video/or/webcam --load_model ../models/ctdet_coco_dla_2x.pth --exp_wo --exp_wo_dim 512
Davide Sapienza's avatar
Davide Sapienza committed
162
```
Micaela Verucchi's avatar
Micaela Verucchi committed
163
### 4)Export weights for MobileNetSSD
Micaela Verucchi's avatar
Micaela Verucchi committed
164
To get the weights needed to run Mobilenet tests use [this](https://github.com/mive93/pytorch-ssd) fork of a Pytorch implementation of SSD network. 
Davide Sapienza's avatar
Davide Sapienza committed
165
166

```
Micaela Verucchi's avatar
Micaela Verucchi committed
167
168
169
170
git clone https://github.com/mive93/pytorch-ssd
cd pytorch-ssd
conda env create -f env_mobv2ssd.yml
python run_ssd_live_demo.py mb2-ssd-lite <pth-model-fil> <labels-file>
Davide Sapienza's avatar
Davide Sapienza committed
171
```
Francesco Gatti's avatar
Francesco Gatti committed
172
173
174
175
176
177
178
179

## Darknet Parser
tkDNN implement and easy parser for darknet cfg files, a network can be converted with *tk::dnn::darknetParser*:
```
// example of parsing yolo4
tk::dnn::Network *net = tk::dnn::darknetParser("yolov4.cfg", "yolov4/layers", "coco.names");
net->print();
```
micaela's avatar
micaela committed
180
All models from darknet are now parsed directly from cfg, you still need to export the weights with the described tools in the previous section.
Francesco Gatti's avatar
Francesco Gatti committed
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
<details>
  <summary>Supported layers</summary>
  convolutional
  maxpool
  avgpool
  shortcut
  upsample
  route
  reorg
  region
  yolo
</details>
<details>
  <summary>Supported activations</summary>
  relu
  leaky
  mish
</details>

Micaela Verucchi's avatar
Micaela Verucchi committed
200
201
## Run the demo 
This is an example using yolov4.
Davide Sapienza's avatar
Davide Sapienza committed
202

Micaela Verucchi's avatar
Micaela Verucchi committed
203
To run the an object detection first create the .rt file by running:
Davide Sapienza's avatar
Davide Sapienza committed
204
```
Micaela Verucchi's avatar
Micaela Verucchi committed
205
206
207
208
209
210
211
rm yolo4_fp32.rt        # be sure to delete(or move) old tensorRT files
./test_yolo4            # run the yolo test (is slow)
```
If you get problems in the creation, try to check the error activating the debug of TensorRT in this way:
```
cmake .. -DDEBUG=True
make
Davide Sapienza's avatar
Davide Sapienza committed
212
```
Micaela Verucchi's avatar
Micaela Verucchi committed
213

micaela's avatar
micaela committed
214
Once you have successfully created your rt file, run the demo: 
Micaela Verucchi's avatar
Micaela Verucchi committed
215
216
217
```
./demo yolo4_fp32.rt ../demo/yolo_test.mp4 y
```
218
In general the demo program takes 7 parameters:
Davide Sapienza's avatar
Davide Sapienza committed
219
```
220
./demo <network-rt-file> <path-to-video> <kind-of-network> <number-of-classes> <n-batches> <show-flag>
221
```
Micaela Verucchi's avatar
Micaela Verucchi committed
222
223
224
225
where
*  ```<network-rt-file>``` is the rt file generated by a test
*  ```<<path-to-video>``` is the path to a video file or a camera input  
*  ```<kind-of-network>``` is the type of network. Thee types are currently supported: ```y``` (YOLO family), ```c``` (CenterNet family) and ```m``` (MobileNet-SSD family)
226
*  ```<number-of-classes>```is the number of classes the network is trained on
227
228
*  ```<n-batches>``` number of batches to use in inference (N.B. you should first export TKDNN_BATCHSIZE to the required n_batches and create again the rt file for the network).
*  ```<show-flag>``` if set to 0 the demo will not show the visualization but save the video into result.mp4 (if n-batches ==1)
229
*  ```<conf-thresh>``` confidence threshold for the detector. Only bounding boxes with threshold greater than conf-thresh will be displayed.
230

Davide Sapienza's avatar
Davide Sapienza committed
231
N.b. By default it is used FP32 inference
Micaela Verucchi's avatar
Micaela Verucchi committed
232

Micaela Verucchi's avatar
Micaela Verucchi committed
233

Micaela Verucchi's avatar
Micaela Verucchi committed
234
![demo](https://user-images.githubusercontent.com/11562617/72547657-540e7800-388d-11ea-83c6-49dfea2a0607.gif)
235

Davide Sapienza's avatar
Davide Sapienza committed
236
237
238
239
240
### FP16 inference

To run the an object detection demo with FP16 inference follow these steps (example with yolov3):
```
export TKDNN_MODE=FP16  # set the half floating point optimization
Francesco Gatti's avatar
Francesco Gatti committed
241
rm yolo3_fp16.rt        # be sure to delete(or move) old tensorRT files
Davide Sapienza's avatar
Davide Sapienza committed
242
./test_yolo3            # run the yolo test (is slow)
Francesco Gatti's avatar
Francesco Gatti committed
243
./demo yolo3_fp16.rt ../demo/yolo_test.mp4 y
Davide Sapienza's avatar
Davide Sapienza committed
244
245
246
247
248
```
N.b. Using FP16 inference will lead to some errors in the results (first or second decimal). 

### INT8 inference

Micaela Verucchi's avatar
Micaela Verucchi committed
249
250
251
252
253
254
To run the an object detection demo with INT8 inference three environment variables need to be set:
  * ```export TKDNN_MODE=INT8```: set the 8-bit integer optimization
  * ```export TKDNN_CALIB_IMG_PATH=/path/to/calibration/image_list.txt``` : image_list.txt has in each line the absolute path to a calibration image
  * ```export TKDNN_CALIB_LABEL_PATH=/path/to/calibration/label_list.txt```: label_list.txt has in each line the absolute path to a calibration label
  
You should provide image_list.txt and label_list.txt, using training images. However, if you want to quickly test the INT8 inference you can run (from this repo root folder)
Davide Sapienza's avatar
Davide Sapienza committed
255
```
Micaela Verucchi's avatar
Micaela Verucchi committed
256
257
bash scripts/download_validation.sh COCO
```
micaela's avatar
micaela committed
258
to automatically download COCO2017 validation (inside demo folder) and create those needed file. Use BDD instead of COCO to download BDD validation. 
Davide Sapienza's avatar
Davide Sapienza committed
259

Micaela Verucchi's avatar
Micaela Verucchi committed
260
261
262
263
264
Then a complete example using yolo3 and COCO dataset would be:
```
export TKDNN_MODE=INT8
export TKDNN_CALIB_LABEL_PATH=../demo/COCO_val2017/all_labels.txt
export TKDNN_CALIB_IMG_PATH=../demo/COCO_val2017/all_images.txt
Francesco Gatti's avatar
Francesco Gatti committed
265
rm yolo3_int8.rt        # be sure to delete(or move) old tensorRT files
Davide Sapienza's avatar
Davide Sapienza committed
266
./test_yolo3            # run the yolo test (is slow)
Francesco Gatti's avatar
Francesco Gatti committed
267
./demo yolo3_int8.rt ../demo/yolo_test.mp4 y
Davide Sapienza's avatar
Davide Sapienza committed
268
```
Micaela Verucchi's avatar
Micaela Verucchi committed
269
270
271
272
273
N.B. 
 * Using INT8 inference will lead to some errors in the results. 
 * The test will be slower: this is due to the INT8 calibration, which may take some time to complete. 
 * INT8 calibration requires TensorRT version greater than or equal to 6.0
 * Only 100 images are used to create the calibration table by default (set in the code).
Davide Sapienza's avatar
Davide Sapienza committed
274

275
276
277
### BatchSize bigger than 1
```
export TKDNN_BATCHSIZE=2
Francesco Gatti's avatar
Francesco Gatti committed
278
279
# build tensorRT files
```
micaela's avatar
micaela committed
280
281
This will create a TensorRT file with the desired **max** batch size.
The test will still run with a batch of 1, but the created tensorRT can manage the desired batch size.
Francesco Gatti's avatar
Francesco Gatti committed
282
283

### Test batch Inference
Francesco Gatti's avatar
Francesco Gatti committed
284
This will test the network with random input and check if the output of each batch is the same.
Francesco Gatti's avatar
Francesco Gatti committed
285
286
287
288
289
290
291
292
293
```
./test_rtinference <network-rt-file> <number-of-batches>
# <number-of-batches> should be less or equal to the max batch size of the <network-rt-file>

# example
export TKDNN_BATCHSIZE=4           # set max batch size
rm yolo3_fp32.rt                   # be sure to delete(or move) old tensorRT files
./test_yolo3                       # build RT file
./test_rtinference yolo3_fp32.rt 4 # test with a batch size of 4
294
295
```

296
## mAP demo
Davide Sapienza's avatar
Davide Sapienza committed
297

298
299
To compute mAP, precision, recall and f1score, run the map_demo.

300
301
A validation set is needed. 
To download COCO_val2017 (80 classes) run (form the root folder): 
xavier's avatar
xavier committed
302
```
303
bash scripts/download_validation.sh COCO
xavier's avatar
xavier committed
304
```
305
306
307
308
309
To download Berkeley_val (10 classes) run (form the root folder): 
```
bash scripts/download_validation.sh BDD
```

xavier's avatar
xavier committed
310
To compute the map, the following parameters are needed:
311
```
Micaela Verucchi's avatar
Micaela Verucchi committed
312
./map_demo <network rt> <network type [y|c|m]> <labels file path> <config file path>
313
314
```
where 
Micaela Verucchi's avatar
Micaela Verucchi committed
315
* ```<network rt>```: rt file of a chosen network on which compute the mAP.
Micaela Verucchi's avatar
Micaela Verucchi committed
316
* ```<network type [y|c|m]>```: type of network. Right now only y(yolo), c(centernet) and m(mobilenet) are allowed
Micaela Verucchi's avatar
Micaela Verucchi committed
317
* ```<labels file path>```: path to a text file containing all the paths of the ground-truth labels. It is important that all the labels of the ground-truth are in a folder called 'labels'. In the folder containing the folder 'labels' there should be also a folder 'images', containing all the ground-truth images having the same same as the labels. To better understand, if there is a label path/to/labels/000001.txt there should be a corresponding image path/to/images/000001.jpg. 
Micaela Verucchi's avatar
Micaela Verucchi committed
318
* ```<config file path>```: path to a yaml file with the parameters needed for the mAP computation, similar to demo/config.yaml
319
320
321
322

Example:

```
xavier's avatar
xavier committed
323
cd build
Davide Sapienza's avatar
Davide Sapienza committed
324
./map_demo dla34_cnet_FP32.rt c ../demo/COCO_val2017/all_labels.txt ../demo/config.yaml
xavier's avatar
xavier committed
325
```
Micaela Verucchi's avatar
Micaela Verucchi committed
326

micaela's avatar
micaela committed
327
This demo also creates a json file named ```net_name_COCO_res.json``` containing all the detections computed. The detections are in COCO format, the correct format to submit the results to [CodaLab COCO detection challenge](https://competitions.codalab.org/competitions/20794#participate).
328

Micaela Verucchi's avatar
Micaela Verucchi committed
329
## Existing tests and supported networks
Micaela Verucchi's avatar
Micaela Verucchi committed
330
331
332

| Test Name         | Network                                       | Dataset                                                       | N Classes | Input size    | Weights                                                                   |
| :---------------- | :-------------------------------------------- | :-----------------------------------------------------------: | :-------: | :-----------: | :------------------------------------------------------------------------ |
Micaela Verucchi's avatar
Micaela Verucchi committed
333
| yolo              | YOLO v2<sup>1</sup>                           | [COCO 2014](http://cocodataset.org/)                          | 80        | 608x608       | [weights](https://cloud.hipert.unimore.it/s/nf4PJ3k8bxBETwL/download)                                                                   |
Micaela Verucchi's avatar
Micaela Verucchi committed
334
335
336
| yolo_224          | YOLO v2<sup>1</sup>                           | [COCO 2014](http://cocodataset.org/)                          | 80        | 224x224       | weights                                                                   |
| yolo_berkeley     | YOLO v2<sup>1</sup>                           | [BDD100K  ](https://bair.berkeley.edu/blog/2018/05/30/bdd/)   | 10        | 416x736       | weights                                                                   |
| yolo_relu         | YOLO v2 (with ReLU, not Leaky)<sup>1</sup>    | [COCO 2014](http://cocodataset.org/)                          | 80        | 416x416       | weights                                                                   |
Micaela Verucchi's avatar
Micaela Verucchi committed
337
| yolo_tiny         | YOLO v2 tiny<sup>1</sup>                      | [COCO 2014](http://cocodataset.org/)                          | 80        | 416x416       | [weights](https://cloud.hipert.unimore.it/s/m3orfJr8pGrN5mQ/download)                                                                   |
Micaela Verucchi's avatar
Micaela Verucchi committed
338
| yolo_voc          | YOLO v2<sup>1</sup>                           | [VOC      ](http://host.robots.ox.ac.uk/pascal/VOC/)          | 21        | 416x416       | [weights](https://cloud.hipert.unimore.it/s/DJC5Fi2pEjfNDP9/download)                                                                   |
Micaela Verucchi's avatar
Micaela Verucchi committed
339
| yolo3             | YOLO v3<sup>2</sup>                           | [COCO 2014](http://cocodataset.org/)                          | 80        | 416x416       | [weights](https://cloud.hipert.unimore.it/s/jPXmHyptpLoNdNR/download)     |
340
| yolo3_512   | YOLO v3<sup>2</sup>                                 | [COCO 2017](http://cocodataset.org/)                          | 80        | 512x512       | [weights](https://cloud.hipert.unimore.it/s/RGecMeGLD4cXEWL/download)     |
Micaela Verucchi's avatar
Micaela Verucchi committed
341
| yolo3_berkeley    | YOLO v3<sup>2</sup>                           | [BDD100K  ](https://bair.berkeley.edu/blog/2018/05/30/bdd/)   | 10        | 320x544       | [weights](https://cloud.hipert.unimore.it/s/o5cHa4AjTKS64oD/download)                                                                   |
Micaela Verucchi's avatar
Micaela Verucchi committed
342
343
| yolo3_coco4       | YOLO v3<sup>2</sup>                           | [COCO 2014](http://cocodataset.org/)                          | 4         | 416x416       | [weights](https://cloud.hipert.unimore.it/s/o27NDzSAartbyc4/download)                                                                   |
| yolo3_flir        | YOLO v3<sup>2</sup>                           | [FREE FLIR](https://www.flir.com/oem/adas/adas-dataset-form/) | 3         | 320x544       | [weights](https://cloud.hipert.unimore.it/s/62DECncmF6bMMiH/download)                                                                   |
Micaela Verucchi's avatar
Micaela Verucchi committed
344
| yolo3_tiny        | YOLO v3 tiny<sup>2</sup>                      | [COCO 2014](http://cocodataset.org/)                          | 80        | 416x416       | [weights](https://cloud.hipert.unimore.it/s/LMcSHtWaLeps8yN/download)     |
345
| yolo3_tiny512     | YOLO v3 tiny<sup>2</sup>                      | [COCO 2017](http://cocodataset.org/)                          | 80        | 512x512       | [weights](https://cloud.hipert.unimore.it/s/8Zt6bHwHADqP4JC/download)     |
Micaela Verucchi's avatar
Micaela Verucchi committed
346
| dla34             | Deep Leayer Aggreagtion (DLA) 34<sup>3</sup>  | [COCO 2014](http://cocodataset.org/)                          | 80        | 224x224       | weights                                                                   |
Micaela Verucchi's avatar
Micaela Verucchi committed
347
| dla34_cnet        | Centernet (DLA34 backend)<sup>4</sup>         | [COCO 2017](http://cocodataset.org/)                          | 80        | 512x512       | [weights](https://cloud.hipert.unimore.it/s/KRZBbCQsKAtQwpZ/download)     |
Micaela Verucchi's avatar
Micaela Verucchi committed
348
| mobilenetv2ssd    | Mobilnet v2 SSD Lite<sup>5</sup>              | [VOC      ](http://host.robots.ox.ac.uk/pascal/VOC/)          | 21        | 300x300       | [weights](https://cloud.hipert.unimore.it/s/x4ZfxBKN23zAJQp/download)     |
349
| mobilenetv2ssd512 | Mobilnet v2 SSD Lite<sup>5</sup>              | [COCO 2017](http://cocodataset.org/)                          | 81        | 512x512       | [weights](https://cloud.hipert.unimore.it/s/pdCw2dYyHMJrcEM/download)     |
Micaela Verucchi's avatar
Micaela Verucchi committed
350
| resnet101         | Resnet 101<sup>6</sup>                        | [COCO 2014](http://cocodataset.org/)                          | 80        | 224x224       | weights                                                                   |
Micaela Verucchi's avatar
Micaela Verucchi committed
351
| resnet101_cnet    | Centernet (Resnet101 backend)<sup>4</sup>     | [COCO 2017](http://cocodataset.org/)                          | 80        | 512x512       | [weights](https://cloud.hipert.unimore.it/s/5BTjHMWBcJk8g3i/download)     |
Micaela Verucchi's avatar
Micaela Verucchi committed
352
| csresnext50-panet-spp    | Cross Stage Partial Network <sup>7</sup>     | [COCO 2014](http://cocodataset.org/)                          | 80        | 416x416       | [weights](https://cloud.hipert.unimore.it/s/Kcs4xBozwY4wFx8/download)     |
Micaela Verucchi's avatar
Micaela Verucchi committed
353
| yolo4             | Yolov4 <sup>8</sup>                           | [COCO 2017](http://cocodataset.org/)                          | 80        | 416x416       | [weights](https://cloud.hipert.unimore.it/s/d97CFzYqCPCp5Hg/download)     |
Francesco Gatti's avatar
Francesco Gatti committed
354
| yolo4_berkeley             | Yolov4 <sup>8</sup>                           | [BDD100K  ](https://bair.berkeley.edu/blog/2018/05/30/bdd/)                          | 10        | 540x320       | [weights](https://cloud.hipert.unimore.it/s/nkWFa5fgb4NTdnB/download)     |
Micaela Verucchi's avatar
Micaela Verucchi committed
355
356
| yolo4tiny             | Yolov4 tiny <sup>9</sup>                           | [COCO 2017](http://cocodataset.org/)                          | 80        | 416x416       | [weights](https://cloud.hipert.unimore.it/s/iRnc4pSqmx78gJs/download)     |
| yolo4x             | Yolov4x-mish  <sup>9</sup>                          | [COCO 2017](http://cocodataset.org/)                          | 80        | 672x672       | [weights](https://cloud.hipert.unimore.it/s/BLPpiAigZJLorQD/download)     |
Micaela Verucchi's avatar
Micaela Verucchi committed
357
358
359
360
361
362
363
364
365


## References

1. Redmon, Joseph, and Ali Farhadi. "YOLO9000: better, faster, stronger." Proceedings of the IEEE conference on computer vision and pattern recognition. 2017.
2. Redmon, Joseph, and Ali Farhadi. "Yolov3: An incremental improvement." arXiv preprint arXiv:1804.02767 (2018).
3. Yu, Fisher, et al. "Deep layer aggregation." Proceedings of the IEEE conference on computer vision and pattern recognition. 2018.
4. Zhou, Xingyi, Dequan Wang, and Philipp Krähenbühl. "Objects as points." arXiv preprint arXiv:1904.07850 (2019).
5. Sandler, Mark, et al. "Mobilenetv2: Inverted residuals and linear bottlenecks." Proceedings of the IEEE conference on computer vision and pattern recognition. 2018.
Micaela Verucchi's avatar
Micaela Verucchi committed
366
6. He, Kaiming, et al. "Deep residual learning for image recognition." Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.
Micaela Verucchi's avatar
Micaela Verucchi committed
367
7. Wang, Chien-Yao, et al. "CSPNet: A New Backbone that can Enhance Learning Capability of CNN." arXiv preprint arXiv:1911.11929 (2019).
Micaela Verucchi's avatar
Micaela Verucchi committed
368
8. Bochkovskiy, Alexey, Chien-Yao Wang, and Hong-Yuan Mark Liao. "YOLOv4: Optimal Speed and Accuracy of Object Detection." arXiv preprint arXiv:2004.10934 (2020).
Micaela Verucchi's avatar
Micaela Verucchi committed
369
9. Bochkovskiy, Alexey, "Yolo v4, v3 and v2 for Windows and Linux" (https://github.com/AlexeyAB/darknet)