有ncnn测试代码吗?我这里测试自己的图片时输出的值的正确率很低,但是在insightFace那里验证时正确率99.5%左右

[youyicloud]

有ncnn测试代码吗?我这里测试自己的图片时输出的值的正确率很低,但是在insightFace那里验证时正确率99.5%左右

[moli232777144]

有几个细节你排查下：
1.mtcnn检测，校正点使用的是sphere的五点对齐，112*112的在横坐标需+8；
2.ncnn模型不需要归一化预处理，mxnet直转的模型已包括该步骤；
3.初步测试lfw是否为同一个人的阈值应该在0.3左右；
4.移植全流程肯定会存在一定精度损失，建议直接用裁剪校正后的lfw图像先刷一遍识别率；

[youyicloud]

@moli232777144 谢谢大佬，没想到你这么认真回复。我目前用的是欧式距离，但是识别出来通一个人的都有2点几到3点几，你用的是什么距离呢？我没有做归一化处理，用的是insightface训练的模型，我下载了lfw数据后，用insightface里的align成112*112了,然后用insightface里的eval目录下的代码加载mobilefacenet测试了align后的正确率都有99.5%,然后移植到ncnn后，输出的值就完全不对。

[youyicloud]

@moli232777144 你计算的是什么距离呢？输出节点是fc1吧？

[moli232777144]

余弦距离，输出fc1

[youyicloud]

好的，谢啦，我再试试

[youyicloud]

我用mxnet计算了一下fc1输出的值的余弦距离,结果还是不对.模型用的是从insightface下载的模型(地址),然后图片用的是完全不同的男女两个人,已经用mtcnn对齐了的lfw里的图片.

`#coding=utf-8
import mxnet as mx
import numpy as np
import math
import cv2
from collections import namedtuple
from sklearn import preprocessing
Batch= namedtuple('Batch', ['data'])

image_size = (112,112)
batch_size = 2

def load_model(model_prefix):
sym, arg_params, aux_params = mx.model.load_checkpoint(model_prefix, 0)
all_layers = sym.get_internals()
sym = all_layers['fc1_output']
model = mx.mod.Module(symbol=sym, label_names = None)
model.bind(data_shapes=[('data', (2, 3, image_size[0], image_size[1]))])
model.set_params(arg_params, aux_params)
return model

def dis(x,y):
return np.dot(x, y)/np.linalg.norm(x)/np.linalg.norm(y)

def test(model_prefix):
img_path_1 = "./img_test/41.jpg"
img_path_2 = "./img_test/31.jpg"
model = load_model(model_prefix)
img1 = cv2.cvtColor(cv2.imread(img_path_1), cv2.COLOR_BGR2RGB)
img1 = cv2.resize(img1, (112, 112), interpolation=cv2.INTER_CUBIC)
img2 = cv2.cvtColor(cv2.imread(img_path_2), cv2.COLOR_BGR2RGB)
img2 = cv2.resize(img2, (112, 112), interpolation=cv2.INTER_CUBIC)
img1 = np.transpose(img1, axes=(2, 0, 1))
img2 = np.transpose(img2, axes=(2, 0, 1))
data_batch = []
data_batch.append(img1)
data_batch.append(img2)
data_batch = np.array(data_batch)
print(data_batch.shape)
print(img2.shape)
model.forward(Batch([mx.nd.array(data_batch)]))
prob = model.get_outputs()[0].asnumpy()
print(dis(prob[0],prob[1]))

model_prefix = "../../models/model"
test(model_prefix)`

上面是代码,下面是输出,

[00:19:53] src/nnvm/legacy_json_util.cc:190: Loading symbol saved by previous version v1.0.0. Attempting to upgra de... [00:19:53] src/nnvm/legacy_json_util.cc:198: Symbol successfully upgraded! (2, 3, 112, 112) (3, 112, 112) -0.9996472
您能帮我看看问题出哪里吗?麻烦啦~ @moli232777144

[w840401]

我用mxnet计算了一下fc1输出的值的余弦距离,结果还是不对.模型用的是从insightface下载的模型(地址),然后图片用的是完全不同的男女两个人,已经用mtcnn对齐了的lfw里的图片.

`#coding=utf-8
import mxnet as mx
import numpy as np
import math
import cv2
from collections import namedtuple
from sklearn import preprocessing
Batch= namedtuple('Batch', ['data'])

image_size = (112,112)
batch_size = 2

def load_model(model_prefix):
sym, arg_params, aux_params = mx.model.load_checkpoint(model_prefix, 0)
all_layers = sym.get_internals()
sym = all_layers['fc1_output']
model = mx.mod.Module(symbol=sym, label_names = None)
model.bind(data_shapes=[('data', (2, 3, image_size[0], image_size[1]))])
model.set_params(arg_params, aux_params)
return model

def dis(x,y):
return np.dot(x, y)/np.linalg.norm(x)/np.linalg.norm(y)

def test(model_prefix):
img_path_1 = "./img_test/41.jpg"
img_path_2 = "./img_test/31.jpg"
model = load_model(model_prefix)
img1 = cv2.cvtColor(cv2.imread(img_path_1), cv2.COLOR_BGR2RGB)
img1 = cv2.resize(img1, (112, 112), interpolation=cv2.INTER_CUBIC)
img2 = cv2.cvtColor(cv2.imread(img_path_2), cv2.COLOR_BGR2RGB)
img2 = cv2.resize(img2, (112, 112), interpolation=cv2.INTER_CUBIC)
img1 = np.transpose(img1, axes=(2, 0, 1))
img2 = np.transpose(img2, axes=(2, 0, 1))
data_batch = []
data_batch.append(img1)
data_batch.append(img2)
data_batch = np.array(data_batch)
print(data_batch.shape)
print(img2.shape)
model.forward(Batch([mx.nd.array(data_batch)]))
prob = model.get_outputs()[0].asnumpy()
print(dis(prob[0],prob[1]))

model_prefix = "../../models/model"
test(model_prefix)`

上面是代码,下面是输出,

[00:19:53] src/nnvm/legacy_json_util.cc:190: Loading symbol saved by previous version v1.0.0. Attempting to upgra de... [00:19:53] src/nnvm/legacy_json_util.cc:198: Symbol successfully upgraded! (2, 3, 112, 112) (3, 112, 112) -0.9996472
您能帮我看看问题出哪里吗?麻烦啦~ @moli232777144

請問有成功測試出來了嗎
可以分享嗎?
感激不盡