NanjingForestryUniversity/supermachine-wood
3
0
Fork 0
mirror of https://github.com/NanjingForestryUniversity/supermachine-wood.git synced 2025-11-08 18:23:54 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'github/dual_sock' into dual_sock

Browse Source
This commit is contained in:
FEIJINTI 2023-04-14 16:10:31 +08:00
commit 3815a8e12b
2 changed files with 2 additions and 40 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
QT_test.py
View File

@ -165,6 +165,7 @@ def main():
socket_send_1.send(send_message) socket_send_1.send(send_message)
print('发送成功') print('发送成功')
result = socket_send_2.recv(5) result = socket_send_2.recv(5)
print(result)
new_leng = int.from_bytes(result[1:], byteorder='big') new_leng = int.from_bytes(result[1:], byteorder='big')
result = socket_send_2.recv(new_leng) result = socket_send_2.recv(new_leng)
print(result) print(result)

41
classifer.py
View File

@ -394,45 +394,6 @@ class WoodClass(object):
# dark_name, middle_name, light_name三个list合并 # dark_name, middle_name, light_name三个list合并
img_name = dark_name + middle_name + light_name img_name = dark_name + middle_name + light_name
# # 使用KMeans算法对图片数据进行聚类
# kmeans = KMeans(n_clusters=3, random_state=0).fit(x_data)
# z = kmeans.predict(x_data)
# # 获取聚类后的数据
# dark = x_data[kmeans.labels_ == 0]
# middle = x_data[kmeans.labels_ == 1]
# light = x_data[kmeans.labels_ == 2]
# # 获取数据的均值
# dark_mean = np.mean(dark, axis=0)
# middle_mean = np.mean(middle, axis=0)
# light_mean = np.mean(light, axis=0)
#
# # 按照平均值从小到大排序
# sorted_cluster_indices = np.argsort([dark_mean[0], middle_mean[0], light_mean[0]])
# print('sorted_cluster_indices:', sorted_cluster_indices)
# # 重新编号聚类标签
# sorted_labels = np.zeros(len(kmeans.labels_), dtype=int)
# for i, label in enumerate(kmeans.labels_):
# sorted_labels[i] = sorted_cluster_indices[label]
# # 更新kmeans.labels_
# kmeans.labels_ = sorted_labels
# print('kmeans.labels_:', kmeans.labels_)
# # 获取更新聚类后的数据
# dark_new = x_data[kmeans.labels_ == 0]
# middle_new = x_data[kmeans.labels_ == 1]
# light_new = x_data[kmeans.labels_ == 2]
# # 获取更新数据的均值
# dark_mean_new = np.mean(dark_new, axis=0)
# middle_mean_new = np.mean(middle_new, axis=0)
# light_mean_new = np.mean(light_new, axis=0)
# # 打印每个聚类的平均值
# print('Dark cluster mean:', dark_mean_new)
# print('Middle cluster mean:', middle_mean_new)
# print('Light cluster mean:', light_mean_new)
# # plot_2d
# plt.figure()
# plt.scatter(x_data[:, 0], x_data[:, 1], c=z)
# plt.show()
# 进行色彩数据校正 # 进行色彩数据校正
if self.isCorrect: if self.isCorrect:
x_data = x_data / (self.correct_color + 1e-4) x_data = x_data / (self.correct_color + 1e-4)
@ -546,7 +507,7 @@ class WoodClass(object):
y_data = y_data[sorted_idx] y_data = y_data[sorted_idx]
labels = labels[sorted_idx] labels = labels[sorted_idx]
img_names = [img_names[i] for i in sorted_idx] img_names = [img_names[i] for i in sorted_idx]
mapping = {0: 's', 1: 'z', 2: 'q'} mapping = {0: 'S', 1: 'Z', 2: 'Q'}
y_data = [mapping[i] for i in y_data] y_data = [mapping[i] for i in y_data]
labels = [mapping[i] for i in labels] labels = [mapping[i] for i in labels]
data = [] data = []