update png (#526)

README.md

@@ -43,9 +43,13 @@ Tengine Lite 核心代码由 4 个模块组成：
 
 ### 转换工具
 
-- [预编译版本](https://github.com/OAID/Tengine-Convert-Tools/releases/download/v0.1/tm_convert_tool)：提供 Linux 系统上预编译好的模型转换工具；
+- [预编译版本](https://github.com/OAID/Tengine/releases/download/lite-v1.2/convert_tool.zip)：提供 Ubuntu 18.04 系统上预编译好的模型转换工具；
 - [在线转换版本](https://convertmodel.com/)：基于 WebAssembly 实现（浏览器本地转换，模型不会上传）；
-- [源码编译](https://github.com/OAID/Tengine-Convert-Tools)：参考 **Tengine-Convert-Tools** 项目编译生成。
+- [源码编译](https://github.com/OAID/Tengine-Convert-Tools)：参考 **Tengine-Convert-Tools** 项目编译生成，建议采用。
+
+### 量化工具
+
+- [预编译版本](tools/quantize/README.md)：提供 Ubuntu 18.04 系统上预编译好的模型量化工具，已支持uint8/int8；
 
 ### 速度评估
 
@@ -67,6 +71,7 @@ Tengine Lite 参考和借鉴了下列项目：
 - [MegEngine](https://github.com/MegEngine/MegEngine)
 - [ONNX](https://github.com/onnx/onnx)
 - [ncnn](https://github.com/Tencent/ncnn)
+- [FeatherCNN](https://github.com/Tencent/FeatherCNN)
 - [MNN](https://github.com/alibaba/MNN)
 - [Paddle Lite](https://github.com/PaddlePaddle/Paddle-Lite)
 - [ACL](https://github.com/ARM-software/ComputeLibrary)

doc/roadmap.md

@@ -6,6 +6,6 @@
 - [ ] optimize AutoKernel implement on x86
 - [ ] fix the Float32 bugs of Vulkan 
 - [ ] support the mode type of PaddlePaddle
-- [ ] support the mode type of OneFlow
+- [x] support the mode type of OneFlow
 - [ ] opensource the plugin implement of NPU
-- [ ] add more test case
+- [x] add more test case

src/dev/cpu/op/conv/conv_dw_hcl_mips.c

@@ -17,6 +17,10 @@
  * under the License.
  */
 
+/*
+ * Copyright (c) 2020, Martin Han
+ * Author: hansh-sz@hotmail.com
+ */
 
 #include "sys_port.h"
 #include "module.h"

src/dev/cpu/op/conv/mips/conv_dw_kernel_mips.c

@@ -17,6 +17,10 @@
  * under the License.
  */
 
+/*
+ * Copyright (c) 2020, Martin Han
+ * Author: hansh-sz@hotmail.com
+ */
 
 #include <stdint.h>
 #include <stdlib.h>
@@ -52,7 +56,7 @@ void convdw3x3s1(float* output, float* input, float* _kernel, float* _bias, int
     const int group = channel;
     const float* kernel = _kernel;
 
-    #pragma omp parallel for num_threads(num_thread)
+#pragma omp parallel for num_threads(num_thread)
     for (int g=0; g<group; g++)
     {
         float* out = output + g * c_step_out;
@@ -168,7 +172,7 @@ void convdw3x3s2(float* output, float* input, float* _kernel, float* _bias, int
     const int tailstep = w - 2*outw + w;
     const float* kernel = _kernel;
 
-    #pragma omp parallel for num_threads(num_thread)
+#pragma omp parallel for num_threads(num_thread)
     for (int g=0; g<group; g++)
     {
         float* out = output + g * c_step_out;
@@ -317,6 +321,7 @@ int conv_dw_run(struct ir_tensor* input_tensor, struct ir_tensor* weight_tensor,
     else
     {
         input_tmp = ( float* )sys_malloc(inh_tmp * inw_tmp * group * sizeof(float));
+#pragma omp parallel for num_threads(num_thread)        
         for (int g = 0; g < group; g++)
         {
             float* pad_in  = input + g * inh * inw;

src/dev/cpu/op/conv/mips/conv_dw_kernel_mips.h

@@ -17,6 +17,10 @@
  * under the License.
  */
 
+/*
+ * Copyright (c) 2020, Martin Han
+ * Author: hansh-sz@hotmail.com
+ */
 
 #ifndef __CONV_DW_KERNEL_MIPS_H_
 #define __CONV_DW_KERNEL_MIPS_H_

src/dev/cpu/op/conv/mips/conv_kernel_mips.c

@@ -17,6 +17,10 @@
  * under the License.
  */
 
+/*
+ * Copyright (c) 2020, Martin Han
+ * Author: hansh-sz@hotmail.com
+ */
 
 #include <stdint.h>
 #include <stdlib.h>

src/dev/cpu/op/conv/mips/conv_kernel_mips.h

@@ -17,6 +17,10 @@
  * under the License.
  */
 
+/*
+ * Copyright (c) 2020, Martin Han
+ * Author: hansh-sz@hotmail.com
+ */
 
 #ifndef _CONV_KERNEL_MIPS_H_
 #define _CONV_KERNEL_MIPS_H_

src/dev/cpu/op/conv/mips/wino_conv_kernel_mips.c

@@ -17,6 +17,11 @@
  * under the License.
  */
 
+/*
+ * Copyright (c) 2020, Martin Han
+ * Author: hansh-sz@hotmail.com
+ */
+
 #include <stdint.h>
 #include <stdlib.h>
 #include <math.h>

src/dev/cpu/op/conv/mips/wino_conv_kernel_mips.h

@@ -17,6 +17,10 @@
  * under the License.
  */
 
+/*
+ * Copyright (c) 2020, Martin Han
+ * Author: hansh-sz@hotmail.com
+ */
 
 #ifndef __WINO_CONV_KERNEL_MIPS_H_
 #define __WINO_CONV_KERNEL_MIPS_H_

src/dev/cpu/op/conv/x86/conv_dw_kernel_x86.c

@@ -2552,6 +2552,7 @@ int conv_dw_run(struct ir_tensor* input_tensor, struct ir_tensor* weight_tensor,
     else
     {
         input_tmp = ( float* )sys_malloc(inh_tmp * inw_tmp * group * sizeof(float));
+#pragma omp parallel for num_threads(num_thread)        
         for (int g = 0; g < group; g++)
         {
             float* pad_in = input + g * inh * inw;