update rknn-toolkit2 to 1.0.0

Signed-off-by: Randall Zhuo <randall.zhuo@rock-chips.com>
Change-Id: I48fa3ee1f450bcb3412f456107805f556b2ed717

doc/RKNNToolKit2_OP_Support_v1.0.0.md

@@ -38,25 +38,26 @@ Based on this protocol, the list of Caffe OPs supported by RKNN Toolkit2 Version
 
 | **Operators**        | **Remarks** |
 | -------------------- | ----------- |
-| BatchNorm          |channel: [1, 8192]<br />height: [1, 8192]<br />width: [1, 8176]|
+| BatchNorm           |channel: [1, 8192]<br />height: [1, 8192]<br />width: [1, 8176]|
 | bn (BatchNorm + Scale) |channel: [1, 8192]<br />height: [1, 8192]<br />width: [1, 8176]<br /> according to https://github.com/TimoSaemann/caffe-segnet-cudnn5|
-| BNLL                 ||
-| Concat               |axis: 1,2,3|
-| Convolution          |channel: [1, 8192]<br />kernel height/width: [1, 31]<br />stride height/width: [1, 7]<br />kernels: [1, 8184]<br />pad left/right/top/bottom: [0, 15]<br />group: 1, channel / N <br /><br />|
-| ConvolutionDepthwise |channel:[1, 8192]<br />kernel height/width: [1, 8]<br />stride height/width: [1, 7]<br />kernels: 1<br />pad left/right/top/bottom: [0, 15]|
-| Crop                 ||
-| Deconvolution        |channel: [1, 8192]<br />kernel height/width: [1, 31]<br />stride height/width: 2, 4, 8<br />kernels: [1, 8192]<br />pad left/right/top/bottom: [0, 15]|
+| BNLL                ||
+| Concat              |axis: 1,2,3|
+| Convolution         |channel: [1, 8192]<br />kernel height/width: [1, 31]<br />stride height/width: [1, 7]<br />kernels: [1, 8184]<br />pad left/right/top/bottom: [0, 15]<br />group: 1, channel / N <br /><br />|
+| ConvolutionDepthwise|channel:[1, 8192]<br />kernel height/width: [1, 8]<br />stride height/width: [1, 7]<br />kernels: 1<br />pad left/right/top/bottom: [0, 15]|
+| Crop                ||
+| Deconvolution       |channel: [1, 8192]<br />kernel height/width: [1, 31]<br />stride height/width: 2, 4, 8<br />kernels: [1, 8192]<br />pad left/right/top/bottom: [0, 15]|
 | Dropout             ||
 | Eltwise             |channel: [1, 8192]<br />height: [1, 8192]<br />width: [1, 8176]<br />support broadcast rule: per-layer/channel/element|
 | Flatten             ||
-| InnerProduct      |channel: [1, 8192]|
-| LRN               ||
-| Normalize |dims: 4|
+| InnerProduct        |channel: [1, 8192]|
+| LRN                 ||
+| Normalize           ||
 | Permute             ||
-| Pooling   | **AveragePool**:<br />channel: [1, 8192]<br />kernel height/width: [1, 7]<br />stride height/width: [1, 8]<br />pad left/right/top/bottom: [0, 7]<br /><br />**GlobalAveragePool**:<br />channel: [1, 8192]<br />kernel height/width: [1, 128]<br />stride height/width: [1, 8]<br />pad left/right/top/bottom: [0, 7] <br /><br />**MaxPool/GlobalMaxPool**:<br />channel: [1, 8192]<br />kernel height/width: [1, 7]<br />stride height/width: [1, 8]<br />pad left/right/top/bottom: [0, 7]<br /><br />**MaxPool**: <br />auto_pad only support NOTSET，ceil_mode only support 0，unsupport dilations |
+| Power               ||
+| Pooling             | **AveragePool**:<br />channel: [1, 8192]<br />kernel height/width: [1, 7]<br />stride height/width: [1, 8]<br />pad left/right/top/bottom: [0, 7]<br /><br />**GlobalAveragePool**:<br />channel: [1, 8192]<br />kernel height/width: [1, 128]<br />stride height/width: [1, 8]<br />pad left/right/top/bottom: [0, 7] <br /><br />**MaxPool/GlobalMaxPool**:<br />channel: [1, 8192]<br />kernel height/width: [1, 7]<br />stride height/width: [1, 8]<br />pad left/right/top/bottom: [0, 7]<br /><br />**MaxPool**: <br />auto_pad only support NOTSET，ceil_mode only support 0，unsupport dilations |
 | PRelu               |channel: [1, 8192]<br />height: [1, 8192]<br />width: [1, 8176]<br />slope: per-layer/channel|
-| Proposal           |batch: 1|
-| Reduction          |output dims <= 4|
+| Proposal            |batch: 1|
+| Reduction           |output dims <= 4|
 | Relu                |channel: [1, 8192]<br />height: [1, 8192]<br />width: [1, 8176]|
 | Relu6               |channel: [1, 8192]<br />height: [1, 8192]<br />width: [1, 8176]|
 | Reorg               ||
@@ -66,10 +67,11 @@ Based on this protocol, the list of Caffe OPs supported by RKNN Toolkit2 Version
 | ROIPooling          |according to https://github.com/twmht/caffe-pva-faster-rcnn|
 | Scale               |channel: [1, 8192]<br />height: [1, 8192]<br />width: [1, 8176]|
 | Sigmoid             |channel: [1, 8192]<br />height: [1, 8192]<br />width: [1, 8176]|
-| Slice              ||
+| Slice               ||
 | Softmax             ||
 | Split               ||
 | TanH                |channel: [1, 8192]<br />height: [1, 8192]<br />width: [1, 8176]|
+| Tile                ||
 | Transpose           ||
 | Upsample            |according to https://github.com/SeanQ88/caffe_upsample and https://github.com/TimoSaemann/caffe-segnet-cudnn5|
 
@@ -88,22 +90,25 @@ The list of ONNX OPs supported by RKNN Toolkit2 Version 0.6.0 is as follows:
 | Conv                          |channel: [1, 8192]<br />kernel height/width: [1, 31]<br />stride height/width: [1, 7]<br />kernels: [1, 8184]<br />pad left/right/top/bottom: [0, 15]<br />dilation: [1, 31]<br />group: 1, channel / N|
 | ConvTranspose                 |channel: [1, 8192]<br />kernel height/width: [1, 31]<br />stride height/width: 2, 4, 8<br />kernels: [1, 8192]<br />pad left/right/top/bottom: [0, 15]<br />dilation: [1, 31]<br />group: 1, channel / N|
 | DepthToSpace                  ||
-| Div                            |support broadcast rule: per-element/other|
+| Div                           |support broadcast rule: per-element/other|
 | Flatten                       ||
 | Gemm                          |channel: [1, 8192]<br /> One input should be Const|
 | GlobalAveragePool     |channel: [1, 8192]<br />kernel height/width: [1, 128]<br />stride height/width: [1, 8]<br />pad left/right/top/bottom: [0, 7]|
 | GlobalMaxPool        |channel: [1, 8192]<br />kernel height/width: [1, 7]<br />stride height/width: [1, 8]<br />pad left/right/top/bottom: [0, 7]|
 | Greater                       |support broadcast rule: per-element/other|
+| HardSigmoid                   ||
 | LeakyRelu                     |channel: [1, 8192]<br />height: [1, 8192]<br />width: [1, 8176]|
 | Less                          |support broadcast rule: per-element/other|
-| LpNormalization               |dims: 4|
+| LpNormalization               ||
 | LRN                           ||
 | MatMul                        |channel: [1, 8192]<br />dims: 2|
-| MaxPool               |channel: [1, 8192]<br />kernel height/width: [1, 7]<br />stride height/width: [1, 8]<br />pad left/right/top/bottom: [0, 7]<br />auto_pad only support NOTSET，ceil_mode only support 0，unsupport dilations|
+| Max                           |channel: [1, 8192]<br />height: [1, 8192]<br />width: [1, 8176]<br /> dims=4|
+| MaxPool                       |channel: [1, 8192]<br />kernel height/width: [1, 7]<br />stride height/width: [1, 8]<br />pad left/right/top/bottom: [0, 7]<br />auto_pad only support NOTSET，ceil_mode only support 0，unsupport dilations|
 | MaxRoiPool                    ||
 | MaxUnpool                     |unsupport pad|
 | Mul                           |channel: [1, 8192]<br />height: [1, 8192]<br />width: [1, 8176]<br />support broadcast rule: per-layer/channel/element|
 | Pad                           |pad value should >= 0; pad dims must be 2 when mode is reflect or edge|
+| Pow                           ||
 | PRelu                         |channel: [1, 8192]<br />height: [1, 8192]<br />width: [1, 8176]<br />slope support broadcast rule:: per-layer/channel|
 | ReduceMean                    |output dims <= 4|
 | ReduceSum                     |output dims <= 4|
@@ -118,6 +123,7 @@ The list of ONNX OPs supported by RKNN Toolkit2 Version 0.6.0 is as follows:
 | Split                         ||
 | Squeeze                       ||
 | Tanh                          |channel: [1, 8192]<br />height: [1, 8192]<br />width: [1, 8176]|
+| Tile                          ||
 | Transpose                     ||
 | Upsample (resize)             ||                                            |
 

doc/changelog_v1.0.0.txt

@@ -1,3 +1,24 @@
+2021-4-30
+版本：v1.0.0
+更新内容:
+1. 新功能:
+    1）卷积类的per channel量化功能
+    2）添加了config中custom_string的模型信息设置、img_quant_RGB2BGR设置
+    3）添加了eval performance的性能测试接口
+    4）添加了连板调试功能
+2. OP支持：
+    1) 添加了Caffe新OP支持：Power/Tile/Eltwise(Max)/去除了normalize维度的限制
+    2) 添加了onnx新OP支持:HardSigmoid/Pow/Tile
+3. 修复一些已知的bug：
+    1) 修复了caffe FC的输出shape以及name的错误
+    2) 优化了mmse的量化性能
+    3）修复caffe的Pooling层的输出shape计算错误
+    4）修复了caffe slice丢弃了其中一个输出的inference bug
+    5）修复了caffe scale层的计算错误
+4. 弃置了reorder_channel的config设置，由用户自行保证inference输入数据的channel正确性
+
+
+
 2021-4-2
 版本：v0.7.0
 更新内容:

examples/caffe/mobilenet_v2/test.py

@@ -26,7 +26,7 @@ if __name__ == '__main__':
     
     # pre-process config
     print('--> config model')
-    rknn.config(mean_values=[103.94, 116.78, 123.68], std_values=[58.82, 58.82, 58.82], reorder_channel=True)
+    rknn.config(mean_values=[103.94, 116.78, 123.68], std_values=[58.82, 58.82, 58.82], quant_img_RGB2BGR=True)
     print('done')
 
     # Load tensorflow model
@@ -57,7 +57,6 @@ if __name__ == '__main__':
 
     # Set inputs
     img = cv2.imread('./goldfish_224x224.jpg')
-    img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
 
     print('--> Init runtime environment')
     ret = rknn.init_runtime()

examples/caffe/vgg-ssd/test.py

@@ -160,7 +160,7 @@ if __name__ == '__main__':
 
     # pre-process config
     print('--> config model')
-    rknn.config(mean_values=[103.94, 116.78, 123.68], std_values=[1, 1, 1], reorder_channel=True)
+    rknn.config(mean_values=[103.94, 116.78, 123.68], std_values=[1, 1, 1], quant_img_RGB2BGR=True)
     print('done')
 
     # Load tensorflow model
@@ -191,7 +191,6 @@ if __name__ == '__main__':
 
     # Set inputs
     img = cv2.imread('./road_300x300.jpg')
-    img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
 
     print('--> Init runtime environment')
     ret = rknn.init_runtime()

examples/darknet/yolov3_416x416/test.py

@@ -26,7 +26,7 @@ if __name__ == '__main__':
     
     # pre-process config
     print('--> config model')
-    rknn.config(mean_values=[0, 0, 0], std_values=[255, 255, 255], reorder_channel=False)
+    rknn.config(mean_values=[0, 0, 0], std_values=[255, 255, 255])
     print('done')
 
     # Load tensorflow model
@@ -91,8 +91,8 @@ if __name__ == '__main__':
     if boxes is not None:
         draw(image, boxes, scores, classes)
 
-    cv2.imshow("results", image)
-    cv2.waitKeyEx(0)
+    print('Save results to results.jpg!')
+    cv2.imwrite('results.jpg', image)
 
     rknn.release()
 

examples/load_quantized_model/test.py

@@ -101,7 +101,7 @@ if __name__ == '__main__':
         print('done')
     # pre-process config
     print('--> Config model')
-    rknn.config(reorder_channel=False)
+    rknn.config()
     print('done')
 
     # Load tensorflow model

examples/onnx/resnet50v2/test.py

@@ -80,7 +80,7 @@ if __name__ == '__main__':
         print('done')
 
     # print('--> config model')
-    rknn.config(mean_values=[123.675, 116.28, 103.53], std_values=[58.82, 58.82, 58.82], reorder_channel=False)
+    rknn.config(mean_values=[123.675, 116.28, 103.53], std_values=[58.82, 58.82, 58.82])
     print('done')
 
     # Load model

examples/pytorch/resnet18/test.py

@@ -50,7 +50,7 @@ if __name__ == '__main__':
 
     # pre-process config
     print('--> config model')
-    rknn.config(mean_values=[123.675, 116.28, 103.53], std_values=[58.395, 58.395, 58.395], reorder_channel=False)
+    rknn.config(mean_values=[123.675, 116.28, 103.53], std_values=[58.395, 58.395, 58.395])
     print('done')
 
     # Load pytorch model

examples/tensorflow/ssd_mobilenet_v1/test.py

@@ -60,7 +60,7 @@ if __name__ == '__main__':
     rknn = RKNN()
 
     # Config for Model Input PreProcess
-    rknn.config(mean_values=[127.5, 127.5, 127.5], std_values=[127.5, 127.5, 127.5], reorder_channel=False)
+    rknn.config(mean_values=[127.5, 127.5, 127.5], std_values=[127.5, 127.5, 127.5])
 
     # Load TensorFlow Model
     print('--> Loading model')

examples/tflite/mobilenet_v1/test.py

@@ -24,11 +24,11 @@ def show_outputs(outputs):
 if __name__ == '__main__':
 
     # Create RKNN object
-    rknn = RKNN(verbose=True)
+    rknn = RKNN()
 
     # pre-process config
     print('--> config model')
-    rknn.config(mean_values=[128, 128, 128], std_values=[128, 128, 128], reorder_channel=False)
+    rknn.config(mean_values=[128, 128, 128], std_values=[128, 128, 128])
     print('done')
 
     # Load tensorflow model

examples/tflite/mobilenet_v1_quant/test.py

@@ -24,11 +24,11 @@ def show_outputs(outputs):
 if __name__ == '__main__':
 
     # Create RKNN object
-    rknn = RKNN(verbose=True)
+    rknn = RKNN()
 
     # pre-process config
     print('--> config model')
-    rknn.config(mean_values=[128, 128, 128], std_values=[128, 128, 128], reorder_channel=False)
+    rknn.config(mean_values=[128, 128, 128], std_values=[128, 128, 128])
     print('done')
 
     # Load tensorflow model