| [pytorch-faster-rcnn](https://github.com/ruotianluo/pytorch-faster-rcnn) | TITAN Xp | NA | 6fps |
| [pytorch-faster-rcnn](https://github.com/ruotianluo/pytorch-faster-rcnn) | TITAN Xp | 15-17fps | 6fps |
[^1]:make sure you install cupy correctly and only one program run on the GPU.
[^1]:make sure you install cupy correctly and only one program run on the GPU. The training speed is sensitive to your gpu status. Moreever it's slow in the start of the program.
It could be even faster by removing visualization, logging, averaging loss etc.
It could be even faster by removing visualization, logging, averaging loss etc.
## Install dependencies
## Install dependencies
...
@@ -57,14 +57,14 @@ requires python3 and PyTorch 0.3
...
@@ -57,14 +57,14 @@ requires python3 and PyTorch 0.3
- Optional, but strongly recommended: build cython code `nms_gpu_post`:
- Optional, but strongly recommended: build cython code `nms_gpu_post`:
```Python
```Bash
cd model/utils/nms/
cd model/utils/nms/
python3 build.py build_ext --inplace
python3 build.py build_ext --inplace
```
```
- start vidom for visualize
- start vidom for visualize
```
```Bash
nohup python3 -m visdom.server &
nohup python3 -m visdom.server &
```
```
...
@@ -85,7 +85,7 @@ See [demo.ipynb](https://github.com/chenyuntc/simple-faster-rcnn-pytorch/blob/ma
...
@@ -85,7 +85,7 @@ See [demo.ipynb](https://github.com/chenyuntc/simple-faster-rcnn-pytorch/blob/ma
1. Download the training, validation, test data and VOCdevkit
1. Download the training, validation, test data and VOCdevkit
@@ -93,7 +93,7 @@ See [demo.ipynb](https://github.com/chenyuntc/simple-faster-rcnn-pytorch/blob/ma
...
@@ -93,7 +93,7 @@ See [demo.ipynb](https://github.com/chenyuntc/simple-faster-rcnn-pytorch/blob/ma
2. Extract all of these tars into one directory named `VOCdevkit`
2. Extract all of these tars into one directory named `VOCdevkit`
```
```Bash
tar xvf VOCtrainval_06-Nov-2007.tar
tar xvf VOCtrainval_06-Nov-2007.tar
tar xvf VOCtest_06-Nov-2007.tar
tar xvf VOCtest_06-Nov-2007.tar
tar xvf VOCdevkit_08-Jun-2007.tar
tar xvf VOCdevkit_08-Jun-2007.tar
...
@@ -101,7 +101,7 @@ See [demo.ipynb](https://github.com/chenyuntc/simple-faster-rcnn-pytorch/blob/ma
...
@@ -101,7 +101,7 @@ See [demo.ipynb](https://github.com/chenyuntc/simple-faster-rcnn-pytorch/blob/ma
3. It should have this basic structure
3. It should have this basic structure
```
```Bash
$VOCdevkit/ # development kit
$VOCdevkit/ # development kit
$VOCdevkit/VOCcode/ # VOC utility code
$VOCdevkit/VOCcode/ # VOC utility code
$VOCdevkit/VOC2007 # image sets, annotations, etc.
$VOCdevkit/VOC2007 # image sets, annotations, etc.
...
@@ -118,7 +118,7 @@ TBD
...
@@ -118,7 +118,7 @@ TBD
If you want to use caffe-pretrain model as initial weight, you can run below to get vgg16 weights converted from caffe, which is the same as the origin paper use.
If you want to use caffe-pretrain model as initial weight, you can run below to get vgg16 weights converted from caffe, which is the same as the origin paper use.
````
````Bash
python misc/convert_caffe_pretrain.py
python misc/convert_caffe_pretrain.py
````
````
...
@@ -156,7 +156,7 @@ Some Key arguments:
...
@@ -156,7 +156,7 @@ Some Key arguments:
you may open browser, type:`http://<ip>:8097` and see the visualization of training procedure as below:
you may open browser, type:`http://<ip>:8097` and see the visualization of training procedure as below:
@@ -181,7 +181,7 @@ This work builds on many excellent works, which include:
...
@@ -181,7 +181,7 @@ This work builds on many excellent works, which include:
-[faster-rcnn.pytorch by Jianwei Yang and Jiasen Lu](https://github.com/jwyang/faster-rcnn.pytorch).It's mainly based on [longcw's faster_rcnn_pytorch](https://github.com/longcw/faster_rcnn_pytorch)
-[faster-rcnn.pytorch by Jianwei Yang and Jiasen Lu](https://github.com/jwyang/faster-rcnn.pytorch).It's mainly based on [longcw's faster_rcnn_pytorch](https://github.com/longcw/faster_rcnn_pytorch)
- All the above Repositories have referred to [py-faster-rcnn by Ross Girshick and Sean Bell](https://github.com/rbgirshick/py-faster-rcnn) either directly or indirectly.
- All the above Repositories have referred to [py-faster-rcnn by Ross Girshick and Sean Bell](https://github.com/rbgirshick/py-faster-rcnn) either directly or indirectly.
## other
## ^_^
Licensed under MIT, see the LICENSE for more detail.
Licensed under MIT, see the LICENSE for more detail.
Contribution Welcome.
Contribution Welcome.
...
@@ -189,3 +189,7 @@ Contribution Welcome.
...
@@ -189,3 +189,7 @@ Contribution Welcome.
If you encounter any problem, feel free to open an issue.
If you encounter any problem, feel free to open an issue.