CV之YOLOv3:基于Tensorflow框架利用YOLOv3算法对热播新剧《庆余年》实现目标检测

简介: CV之YOLOv3:基于Tensorflow框架利用YOLOv3算法对热播新剧《庆余年》实现目标检测


目录

搭建

1、下载代码

2、安装依赖库

3、导出COCO权重解压到checkpoint文件夹内

4、测试


 

 

搭建

1、下载代码

tensorflow-yolov3

2、安装依赖库

pip install -r ./docs/requirements.txt

3、导出COCO权重解压到checkpoint文件夹内

Exporting loaded COCO weights as TF checkpoint(yolov3_coco.ckpt

python convert_weight.py

python freeze_graph.py

 

4、测试

 

1. 2019-12-25 15:05:02.766745: I
2. => yolov3/darknet-53/Conv/weights                     (3, 3, 3, 32)
3. => yolov3/darknet-53/Conv/BatchNorm/gamma             (32,)
4. => yolov3/darknet-53/Conv/BatchNorm/beta              (32,)
5. => yolov3/darknet-53/Conv/BatchNorm/moving_mean       (32,)
6. => yolov3/darknet-53/Conv/BatchNorm/moving_variance   (32,)
7. => yolov3/darknet-53/Conv_1/weights                   (3, 3, 32, 64)
8. => yolov3/darknet-53/Conv_1/BatchNorm/gamma           (64,)
9. => yolov3/darknet-53/Conv_1/BatchNorm/beta            (64,)
10. => yolov3/darknet-53/Conv_1/BatchNorm/moving_mean     (64,)
11. => yolov3/darknet-53/Conv_1/BatchNorm/moving_variance (64,)
12. => yolov3/darknet-53/Conv_2/weights                   (1, 1, 64, 32)
13. => yolov3/darknet-53/Conv_2/BatchNorm/gamma           (32,)
14. => yolov3/darknet-53/Conv_2/BatchNorm/beta            (32,)
15. => yolov3/darknet-53/Conv_2/BatchNorm/moving_mean     (32,)
16. => yolov3/darknet-53/Conv_2/BatchNorm/moving_variance (32,)
17. => yolov3/darknet-53/Conv_3/weights                   (3, 3, 32, 64)
18. => yolov3/darknet-53/Conv_3/BatchNorm/gamma           (64,)
19. => yolov3/darknet-53/Conv_3/BatchNorm/beta            (64,)
20. => yolov3/darknet-53/Conv_3/BatchNorm/moving_mean     (64,)
21. => yolov3/darknet-53/Conv_3/BatchNorm/moving_variance (64,)
22. => yolov3/darknet-53/Conv_4/weights                   (3, 3, 64, 128)
23. => yolov3/darknet-53/Conv_4/BatchNorm/gamma           (128,)
24. => yolov3/darknet-53/Conv_4/BatchNorm/beta            (128,)
25. => yolov3/darknet-53/Conv_4/BatchNorm/moving_mean     (128,)
26. => yolov3/darknet-53/Conv_4/BatchNorm/moving_variance (128,)
27. => yolov3/darknet-53/Conv_5/weights                   (1, 1, 128, 64)
28. => yolov3/darknet-53/Conv_5/BatchNorm/gamma           (64,)
29. => yolov3/darknet-53/Conv_5/BatchNorm/beta            (64,)
30. => yolov3/darknet-53/Conv_5/BatchNorm/moving_mean     (64,)
31. => yolov3/darknet-53/Conv_5/BatchNorm/moving_variance (64,)
32. => yolov3/darknet-53/Conv_6/weights                   (3, 3, 64, 128)
33. => yolov3/darknet-53/Conv_6/BatchNorm/gamma           (128,)
34. => yolov3/darknet-53/Conv_6/BatchNorm/beta            (128,)
35. => yolov3/darknet-53/Conv_6/BatchNorm/moving_mean     (128,)
36. => yolov3/darknet-53/Conv_6/BatchNorm/moving_variance (128,)
37. => yolov3/darknet-53/Conv_7/weights                   (1, 1, 128, 64)
38. => yolov3/darknet-53/Conv_7/BatchNorm/gamma           (64,)
39. => yolov3/darknet-53/Conv_7/BatchNorm/beta            (64,)
40. => yolov3/darknet-53/Conv_7/BatchNorm/moving_mean     (64,)
41. => yolov3/darknet-53/Conv_7/BatchNorm/moving_variance (64,)
42. => yolov3/darknet-53/Conv_8/weights                   (3, 3, 64, 128)
43. => yolov3/darknet-53/Conv_8/BatchNorm/gamma           (128,)
44. => yolov3/darknet-53/Conv_8/BatchNorm/beta            (128,)
45. => yolov3/darknet-53/Conv_8/BatchNorm/moving_mean     (128,)
46. => yolov3/darknet-53/Conv_8/BatchNorm/moving_variance (128,)
47. => yolov3/darknet-53/Conv_9/weights                   (3, 3, 128, 256)
48. => yolov3/darknet-53/Conv_9/BatchNorm/gamma           (256,)
49. => yolov3/darknet-53/Conv_9/BatchNorm/beta            (256,)
50. => yolov3/darknet-53/Conv_9/BatchNorm/moving_mean     (256,)
51. => yolov3/darknet-53/Conv_9/BatchNorm/moving_variance (256,)
52. => yolov3/darknet-53/Conv_10/weights                  (1, 1, 256, 128)
53. => yolov3/darknet-53/Conv_10/BatchNorm/gamma          (128,)
54. => yolov3/darknet-53/Conv_10/BatchNorm/beta           (128,)
55. => yolov3/darknet-53/Conv_10/BatchNorm/moving_mean    (128,)
56. => yolov3/darknet-53/Conv_10/BatchNorm/moving_variance (128,)
57. => yolov3/darknet-53/Conv_11/weights                  (3, 3, 128, 256)
58. => yolov3/darknet-53/Conv_11/BatchNorm/gamma          (256,)
59. => yolov3/darknet-53/Conv_11/BatchNorm/beta           (256,)
60. => yolov3/darknet-53/Conv_11/BatchNorm/moving_mean    (256,)
61. => yolov3/darknet-53/Conv_11/BatchNorm/moving_variance (256,)
62. => yolov3/darknet-53/Conv_12/weights                  (1, 1, 256, 128)
63. => yolov3/darknet-53/Conv_12/BatchNorm/gamma          (128,)
64. => yolov3/darknet-53/Conv_12/BatchNorm/beta           (128,)
65. => yolov3/darknet-53/Conv_12/BatchNorm/moving_mean    (128,)
66. => yolov3/darknet-53/Conv_12/BatchNorm/moving_variance (128,)
67. => yolov3/darknet-53/Conv_13/weights                  (3, 3, 128, 256)
68. => yolov3/darknet-53/Conv_13/BatchNorm/gamma          (256,)
69. => yolov3/darknet-53/Conv_13/BatchNorm/beta           (256,)
70. => yolov3/darknet-53/Conv_13/BatchNorm/moving_mean    (256,)
71. => yolov3/darknet-53/Conv_13/BatchNorm/moving_variance (256,)
72. => yolov3/darknet-53/Conv_14/weights                  (1, 1, 256, 128)
73. => yolov3/darknet-53/Conv_14/BatchNorm/gamma          (128,)
74. => yolov3/darknet-53/Conv_14/BatchNorm/beta           (128,)
75. => yolov3/darknet-53/Conv_14/BatchNorm/moving_mean    (128,)
76. => yolov3/darknet-53/Conv_14/BatchNorm/moving_variance (128,)
77. => yolov3/darknet-53/Conv_15/weights                  (3, 3, 128, 256)
78. => yolov3/darknet-53/Conv_15/BatchNorm/gamma          (256,)
79. => yolov3/darknet-53/Conv_15/BatchNorm/beta           (256,)
80. => yolov3/darknet-53/Conv_15/BatchNorm/moving_mean    (256,)
81. => yolov3/darknet-53/Conv_15/BatchNorm/moving_variance (256,)
82. => yolov3/darknet-53/Conv_16/weights                  (1, 1, 256, 128)
83. => yolov3/darknet-53/Conv_16/BatchNorm/gamma          (128,)
84. => yolov3/darknet-53/Conv_16/BatchNorm/beta           (128,)
85. => yolov3/darknet-53/Conv_16/BatchNorm/moving_mean    (128,)
86. => yolov3/darknet-53/Conv_16/BatchNorm/moving_variance (128,)
87. => yolov3/darknet-53/Conv_17/weights                  (3, 3, 128, 256)
88. => yolov3/darknet-53/Conv_17/BatchNorm/gamma          (256,)
89. => yolov3/darknet-53/Conv_17/BatchNorm/beta           (256,)
90. => yolov3/darknet-53/Conv_17/BatchNorm/moving_mean    (256,)
91. => yolov3/darknet-53/Conv_17/BatchNorm/moving_variance (256,)
92. => yolov3/darknet-53/Conv_18/weights                  (1, 1, 256, 128)
93. => yolov3/darknet-53/Conv_18/BatchNorm/gamma          (128,)
94. => yolov3/darknet-53/Conv_18/BatchNorm/beta           (128,)
95. => yolov3/darknet-53/Conv_18/BatchNorm/moving_mean    (128,)
96. => yolov3/darknet-53/Conv_18/BatchNorm/moving_variance (128,)
97. => yolov3/darknet-53/Conv_19/weights                  (3, 3, 128, 256)
98. => yolov3/darknet-53/Conv_19/BatchNorm/gamma          (256,)
99. => yolov3/darknet-53/Conv_19/BatchNorm/beta           (256,)
100. => yolov3/darknet-53/Conv_19/BatchNorm/moving_mean    (256,)
101. => yolov3/darknet-53/Conv_19/BatchNorm/moving_variance (256,)
102. => yolov3/darknet-53/Conv_20/weights                  (1, 1, 256, 128)
103. => yolov3/darknet-53/Conv_20/BatchNorm/gamma          (128,)
104. => yolov3/darknet-53/Conv_20/BatchNorm/beta           (128,)
105. => yolov3/darknet-53/Conv_20/BatchNorm/moving_mean    (128,)
106. => yolov3/darknet-53/Conv_20/BatchNorm/moving_variance (128,)
107. => yolov3/darknet-53/Conv_21/weights                  (3, 3, 128, 256)
108. => yolov3/darknet-53/Conv_21/BatchNorm/gamma          (256,)
109. => yolov3/darknet-53/Conv_21/BatchNorm/beta           (256,)
110. => yolov3/darknet-53/Conv_21/BatchNorm/moving_mean    (256,)
111. => yolov3/darknet-53/Conv_21/BatchNorm/moving_variance (256,)
112. => yolov3/darknet-53/Conv_22/weights                  (1, 1, 256, 128)
113. => yolov3/darknet-53/Conv_22/BatchNorm/gamma          (128,)
114. => yolov3/darknet-53/Conv_22/BatchNorm/beta           (128,)
115. => yolov3/darknet-53/Conv_22/BatchNorm/moving_mean    (128,)
116. => yolov3/darknet-53/Conv_22/BatchNorm/moving_variance (128,)
117. => yolov3/darknet-53/Conv_23/weights                  (3, 3, 128, 256)
118. => yolov3/darknet-53/Conv_23/BatchNorm/gamma          (256,)
119. => yolov3/darknet-53/Conv_23/BatchNorm/beta           (256,)
120. => yolov3/darknet-53/Conv_23/BatchNorm/moving_mean    (256,)
121. => yolov3/darknet-53/Conv_23/BatchNorm/moving_variance (256,)
122. => yolov3/darknet-53/Conv_24/weights                  (1, 1, 256, 128)
123. => yolov3/darknet-53/Conv_24/BatchNorm/gamma          (128,)
124. => yolov3/darknet-53/Conv_24/BatchNorm/beta           (128,)
125. => yolov3/darknet-53/Conv_24/BatchNorm/moving_mean    (128,)
126. => yolov3/darknet-53/Conv_24/BatchNorm/moving_variance (128,)
127. => yolov3/darknet-53/Conv_25/weights                  (3, 3, 128, 256)
128. => yolov3/darknet-53/Conv_25/BatchNorm/gamma          (256,)
129. => yolov3/darknet-53/Conv_25/BatchNorm/beta           (256,)
130. => yolov3/darknet-53/Conv_25/BatchNorm/moving_mean    (256,)
131. => yolov3/darknet-53/Conv_25/BatchNorm/moving_variance (256,)
132. => yolov3/darknet-53/Conv_26/weights                  (3, 3, 256, 512)
133. => yolov3/darknet-53/Conv_26/BatchNorm/gamma          (512,)
134. => yolov3/darknet-53/Conv_26/BatchNorm/beta           (512,)
135. => yolov3/darknet-53/Conv_26/BatchNorm/moving_mean    (512,)
136. => yolov3/darknet-53/Conv_26/BatchNorm/moving_variance (512,)
137. => yolov3/darknet-53/Conv_27/weights                  (1, 1, 512, 256)
138. => yolov3/darknet-53/Conv_27/BatchNorm/gamma          (256,)
139. => yolov3/darknet-53/Conv_27/BatchNorm/beta           (256,)
140. => yolov3/darknet-53/Conv_27/BatchNorm/moving_mean    (256,)
141. => yolov3/darknet-53/Conv_27/BatchNorm/moving_variance (256,)
142. => yolov3/darknet-53/Conv_28/weights                  (3, 3, 256, 512)
143. => yolov3/darknet-53/Conv_28/BatchNorm/gamma          (512,)
144. => yolov3/darknet-53/Conv_28/BatchNorm/beta           (512,)
145. => yolov3/darknet-53/Conv_28/BatchNorm/moving_mean    (512,)
146. => yolov3/darknet-53/Conv_28/BatchNorm/moving_variance (512,)
147. => yolov3/darknet-53/Conv_29/weights                  (1, 1, 512, 256)
148. => yolov3/darknet-53/Conv_29/BatchNorm/gamma          (256,)
149. => yolov3/darknet-53/Conv_29/BatchNorm/beta           (256,)
150. => yolov3/darknet-53/Conv_29/BatchNorm/moving_mean    (256,)
151. => yolov3/darknet-53/Conv_29/BatchNorm/moving_variance (256,)
152. => yolov3/darknet-53/Conv_30/weights                  (3, 3, 256, 512)
153. => yolov3/darknet-53/Conv_30/BatchNorm/gamma          (512,)
154. => yolov3/darknet-53/Conv_30/BatchNorm/beta           (512,)
155. => yolov3/darknet-53/Conv_30/BatchNorm/moving_mean    (512,)
156. => yolov3/darknet-53/Conv_30/BatchNorm/moving_variance (512,)
157. => yolov3/darknet-53/Conv_31/weights                  (1, 1, 512, 256)
158. => yolov3/darknet-53/Conv_31/BatchNorm/gamma          (256,)
159. => yolov3/darknet-53/Conv_31/BatchNorm/beta           (256,)
160. => yolov3/darknet-53/Conv_31/BatchNorm/moving_mean    (256,)
161. => yolov3/darknet-53/Conv_31/BatchNorm/moving_variance (256,)
162. => yolov3/darknet-53/Conv_32/weights                  (3, 3, 256, 512)
163. => yolov3/darknet-53/Conv_32/BatchNorm/gamma          (512,)
164. => yolov3/darknet-53/Conv_32/BatchNorm/beta           (512,)
165. => yolov3/darknet-53/Conv_32/BatchNorm/moving_mean    (512,)
166. => yolov3/darknet-53/Conv_32/BatchNorm/moving_variance (512,)
167. => yolov3/darknet-53/Conv_33/weights                  (1, 1, 512, 256)
168. => yolov3/darknet-53/Conv_33/BatchNorm/gamma          (256,)
169. => yolov3/darknet-53/Conv_33/BatchNorm/beta           (256,)
170. => yolov3/darknet-53/Conv_33/BatchNorm/moving_mean    (256,)
171. => yolov3/darknet-53/Conv_33/BatchNorm/moving_variance (256,)
172. => yolov3/darknet-53/Conv_34/weights                  (3, 3, 256, 512)
173. => yolov3/darknet-53/Conv_34/BatchNorm/gamma          (512,)
174. => yolov3/darknet-53/Conv_34/BatchNorm/beta           (512,)
175. => yolov3/darknet-53/Conv_34/BatchNorm/moving_mean    (512,)
176. => yolov3/darknet-53/Conv_34/BatchNorm/moving_variance (512,)
177. => yolov3/darknet-53/Conv_35/weights                  (1, 1, 512, 256)
178. => yolov3/darknet-53/Conv_35/BatchNorm/gamma          (256,)
179. => yolov3/darknet-53/Conv_35/BatchNorm/beta           (256,)
180. => yolov3/darknet-53/Conv_35/BatchNorm/moving_mean    (256,)
181. => yolov3/darknet-53/Conv_35/BatchNorm/moving_variance (256,)
182. => yolov3/darknet-53/Conv_36/weights                  (3, 3, 256, 512)
183. => yolov3/darknet-53/Conv_36/BatchNorm/gamma          (512,)
184. => yolov3/darknet-53/Conv_36/BatchNorm/beta           (512,)
185. => yolov3/darknet-53/Conv_36/BatchNorm/moving_mean    (512,)
186. => yolov3/darknet-53/Conv_36/BatchNorm/moving_variance (512,)
187. => yolov3/darknet-53/Conv_37/weights                  (1, 1, 512, 256)
188. => yolov3/darknet-53/Conv_37/BatchNorm/gamma          (256,)
189. => yolov3/darknet-53/Conv_37/BatchNorm/beta           (256,)
190. => yolov3/darknet-53/Conv_37/BatchNorm/moving_mean    (256,)
191. => yolov3/darknet-53/Conv_37/BatchNorm/moving_variance (256,)
192. => yolov3/darknet-53/Conv_38/weights                  (3, 3, 256, 512)
193. => yolov3/darknet-53/Conv_38/BatchNorm/gamma          (512,)
194. => yolov3/darknet-53/Conv_38/BatchNorm/beta           (512,)
195. => yolov3/darknet-53/Conv_38/BatchNorm/moving_mean    (512,)
196. => yolov3/darknet-53/Conv_38/BatchNorm/moving_variance (512,)
197. => yolov3/darknet-53/Conv_39/weights                  (1, 1, 512, 256)
198. => yolov3/darknet-53/Conv_39/BatchNorm/gamma          (256,)
199. => yolov3/darknet-53/Conv_39/BatchNorm/beta           (256,)
200. => yolov3/darknet-53/Conv_39/BatchNorm/moving_mean    (256,)
201. => yolov3/darknet-53/Conv_39/BatchNorm/moving_variance (256,)
202. => yolov3/darknet-53/Conv_40/weights                  (3, 3, 256, 512)
203. => yolov3/darknet-53/Conv_40/BatchNorm/gamma          (512,)
204. => yolov3/darknet-53/Conv_40/BatchNorm/beta           (512,)
205. => yolov3/darknet-53/Conv_40/BatchNorm/moving_mean    (512,)
206. => yolov3/darknet-53/Conv_40/BatchNorm/moving_variance (512,)
207. => yolov3/darknet-53/Conv_41/weights                  (1, 1, 512, 256)
208. => yolov3/darknet-53/Conv_41/BatchNorm/gamma          (256,)
209. => yolov3/darknet-53/Conv_41/BatchNorm/beta           (256,)
210. => yolov3/darknet-53/Conv_41/BatchNorm/moving_mean    (256,)
211. => yolov3/darknet-53/Conv_41/BatchNorm/moving_variance (256,)
212. => yolov3/darknet-53/Conv_42/weights                  (3, 3, 256, 512)
213. => yolov3/darknet-53/Conv_42/BatchNorm/gamma          (512,)
214. => yolov3/darknet-53/Conv_42/BatchNorm/beta           (512,)
215. => yolov3/darknet-53/Conv_42/BatchNorm/moving_mean    (512,)
216. => yolov3/darknet-53/Conv_42/BatchNorm/moving_variance (512,)
217. => yolov3/darknet-53/Conv_43/weights                  (3, 3, 512, 1024)
218. => yolov3/darknet-53/Conv_43/BatchNorm/gamma          (1024,)
219. => yolov3/darknet-53/Conv_43/BatchNorm/beta           (1024,)
220. => yolov3/darknet-53/Conv_43/BatchNorm/moving_mean    (1024,)
221. => yolov3/darknet-53/Conv_43/BatchNorm/moving_variance (1024,)
222. => yolov3/darknet-53/Conv_44/weights                  (1, 1, 1024, 512)
223. => yolov3/darknet-53/Conv_44/BatchNorm/gamma          (512,)
224. => yolov3/darknet-53/Conv_44/BatchNorm/beta           (512,)
225. => yolov3/darknet-53/Conv_44/BatchNorm/moving_mean    (512,)
226. => yolov3/darknet-53/Conv_44/BatchNorm/moving_variance (512,)
227. => yolov3/darknet-53/Conv_45/weights                  (3, 3, 512, 1024)
228. => yolov3/darknet-53/Conv_45/BatchNorm/gamma          (1024,)
229. => yolov3/darknet-53/Conv_45/BatchNorm/beta           (1024,)
230. => yolov3/darknet-53/Conv_45/BatchNorm/moving_mean    (1024,)
231. => yolov3/darknet-53/Conv_45/BatchNorm/moving_variance (1024,)
232. => yolov3/darknet-53/Conv_46/weights                  (1, 1, 1024, 512)
233. => yolov3/darknet-53/Conv_46/BatchNorm/gamma          (512,)
234. => yolov3/darknet-53/Conv_46/BatchNorm/beta           (512,)
235. => yolov3/darknet-53/Conv_46/BatchNorm/moving_mean    (512,)
236. => yolov3/darknet-53/Conv_46/BatchNorm/moving_variance (512,)
237. => yolov3/darknet-53/Conv_47/weights                  (3, 3, 512, 1024)
238. => yolov3/darknet-53/Conv_47/BatchNorm/gamma          (1024,)
239. => yolov3/darknet-53/Conv_47/BatchNorm/beta           (1024,)
240. => yolov3/darknet-53/Conv_47/BatchNorm/moving_mean    (1024,)
241. => yolov3/darknet-53/Conv_47/BatchNorm/moving_variance (1024,)
242. => yolov3/darknet-53/Conv_48/weights                  (1, 1, 1024, 512)
243. => yolov3/darknet-53/Conv_48/BatchNorm/gamma          (512,)
244. => yolov3/darknet-53/Conv_48/BatchNorm/beta           (512,)
245. => yolov3/darknet-53/Conv_48/BatchNorm/moving_mean    (512,)
246. => yolov3/darknet-53/Conv_48/BatchNorm/moving_variance (512,)
247. => yolov3/darknet-53/Conv_49/weights                  (3, 3, 512, 1024)
248. => yolov3/darknet-53/Conv_49/BatchNorm/gamma          (1024,)
249. => yolov3/darknet-53/Conv_49/BatchNorm/beta           (1024,)
250. => yolov3/darknet-53/Conv_49/BatchNorm/moving_mean    (1024,)
251. => yolov3/darknet-53/Conv_49/BatchNorm/moving_variance (1024,)
252. => yolov3/darknet-53/Conv_50/weights                  (1, 1, 1024, 512)
253. => yolov3/darknet-53/Conv_50/BatchNorm/gamma          (512,)
254. => yolov3/darknet-53/Conv_50/BatchNorm/beta           (512,)
255. => yolov3/darknet-53/Conv_50/BatchNorm/moving_mean    (512,)
256. => yolov3/darknet-53/Conv_50/BatchNorm/moving_variance (512,)
257. => yolov3/darknet-53/Conv_51/weights                  (3, 3, 512, 1024)
258. => yolov3/darknet-53/Conv_51/BatchNorm/gamma          (1024,)
259. => yolov3/darknet-53/Conv_51/BatchNorm/beta           (1024,)
260. => yolov3/darknet-53/Conv_51/BatchNorm/moving_mean    (1024,)
261. => yolov3/darknet-53/Conv_51/BatchNorm/moving_variance (1024,)
262. => yolov3/yolo-v3/Conv/weights                        (1, 1, 1024, 512)
263. => yolov3/yolo-v3/Conv/BatchNorm/gamma                (512,)
264. => yolov3/yolo-v3/Conv/BatchNorm/beta                 (512,)
265. => yolov3/yolo-v3/Conv/BatchNorm/moving_mean          (512,)
266. => yolov3/yolo-v3/Conv/BatchNorm/moving_variance      (512,)
267. => yolov3/yolo-v3/Conv_1/weights                      (3, 3, 512, 1024)
268. => yolov3/yolo-v3/Conv_1/BatchNorm/gamma              (1024,)
269. => yolov3/yolo-v3/Conv_1/BatchNorm/beta               (1024,)
270. => yolov3/yolo-v3/Conv_1/BatchNorm/moving_mean        (1024,)
271. => yolov3/yolo-v3/Conv_1/BatchNorm/moving_variance    (1024,)
272. => yolov3/yolo-v3/Conv_2/weights                      (1, 1, 1024, 512)
273. => yolov3/yolo-v3/Conv_2/BatchNorm/gamma              (512,)
274. => yolov3/yolo-v3/Conv_2/BatchNorm/beta               (512,)
275. => yolov3/yolo-v3/Conv_2/BatchNorm/moving_mean        (512,)
276. => yolov3/yolo-v3/Conv_2/BatchNorm/moving_variance    (512,)
277. => yolov3/yolo-v3/Conv_3/weights                      (3, 3, 512, 1024)
278. => yolov3/yolo-v3/Conv_3/BatchNorm/gamma              (1024,)
279. => yolov3/yolo-v3/Conv_3/BatchNorm/beta               (1024,)
280. => yolov3/yolo-v3/Conv_3/BatchNorm/moving_mean        (1024,)
281. => yolov3/yolo-v3/Conv_3/BatchNorm/moving_variance    (1024,)
282. => yolov3/yolo-v3/Conv_4/weights                      (1, 1, 1024, 512)
283. => yolov3/yolo-v3/Conv_4/BatchNorm/gamma              (512,)
284. => yolov3/yolo-v3/Conv_4/BatchNorm/beta               (512,)
285. => yolov3/yolo-v3/Conv_4/BatchNorm/moving_mean        (512,)
286. => yolov3/yolo-v3/Conv_4/BatchNorm/moving_variance    (512,)
287. => yolov3/yolo-v3/Conv_5/weights                      (3, 3, 512, 1024)
288. => yolov3/yolo-v3/Conv_5/BatchNorm/gamma              (1024,)
289. => yolov3/yolo-v3/Conv_5/BatchNorm/beta               (1024,)
290. => yolov3/yolo-v3/Conv_5/BatchNorm/moving_mean        (1024,)
291. => yolov3/yolo-v3/Conv_5/BatchNorm/moving_variance    (1024,)
292. => yolov3/yolo-v3/Conv_6/weights                      (1, 1, 1024, 255)
293. => yolov3/yolo-v3/Conv_6/biases                       (255,)
294. => yolov3/yolo-v3/Conv_7/weights                      (1, 1, 512, 256)
295. => yolov3/yolo-v3/Conv_7/BatchNorm/gamma              (256,)
296. => yolov3/yolo-v3/Conv_7/BatchNorm/beta               (256,)
297. => yolov3/yolo-v3/Conv_7/BatchNorm/moving_mean        (256,)
298. => yolov3/yolo-v3/Conv_7/BatchNorm/moving_variance    (256,)
299. => yolov3/yolo-v3/Conv_8/weights                      (1, 1, 768, 256)
300. => yolov3/yolo-v3/Conv_8/BatchNorm/gamma              (256,)
301. => yolov3/yolo-v3/Conv_8/BatchNorm/beta               (256,)
302. => yolov3/yolo-v3/Conv_8/BatchNorm/moving_mean        (256,)
303. => yolov3/yolo-v3/Conv_8/BatchNorm/moving_variance    (256,)
304. => yolov3/yolo-v3/Conv_9/weights                      (3, 3, 256, 512)
305. => yolov3/yolo-v3/Conv_9/BatchNorm/gamma              (512,)
306. => yolov3/yolo-v3/Conv_9/BatchNorm/beta               (512,)
307. => yolov3/yolo-v3/Conv_9/BatchNorm/moving_mean        (512,)
308. => yolov3/yolo-v3/Conv_9/BatchNorm/moving_variance    (512,)
309. => yolov3/yolo-v3/Conv_10/weights                     (1, 1, 512, 256)
310. => yolov3/yolo-v3/Conv_10/BatchNorm/gamma             (256,)
311. => yolov3/yolo-v3/Conv_10/BatchNorm/beta              (256,)
312. => yolov3/yolo-v3/Conv_10/BatchNorm/moving_mean       (256,)
313. => yolov3/yolo-v3/Conv_10/BatchNorm/moving_variance   (256,)
314. => yolov3/yolo-v3/Conv_11/weights                     (3, 3, 256, 512)
315. => yolov3/yolo-v3/Conv_11/BatchNorm/gamma             (512,)
316. => yolov3/yolo-v3/Conv_11/BatchNorm/beta              (512,)
317. => yolov3/yolo-v3/Conv_11/BatchNorm/moving_mean       (512,)
318. => yolov3/yolo-v3/Conv_11/BatchNorm/moving_variance   (512,)
319. => yolov3/yolo-v3/Conv_12/weights                     (1, 1, 512, 256)
320. => yolov3/yolo-v3/Conv_12/BatchNorm/gamma             (256,)
321. => yolov3/yolo-v3/Conv_12/BatchNorm/beta              (256,)
322. => yolov3/yolo-v3/Conv_12/BatchNorm/moving_mean       (256,)
323. => yolov3/yolo-v3/Conv_12/BatchNorm/moving_variance   (256,)
324. => yolov3/yolo-v3/Conv_13/weights                     (3, 3, 256, 512)
325. => yolov3/yolo-v3/Conv_13/BatchNorm/gamma             (512,)
326. => yolov3/yolo-v3/Conv_13/BatchNorm/beta              (512,)
327. => yolov3/yolo-v3/Conv_13/BatchNorm/moving_mean       (512,)
328. => yolov3/yolo-v3/Conv_13/BatchNorm/moving_variance   (512,)
329. => yolov3/yolo-v3/Conv_14/weights                     (1, 1, 512, 255)
330. => yolov3/yolo-v3/Conv_14/biases                      (255,)
331. => yolov3/yolo-v3/Conv_15/weights                     (1, 1, 256, 128)
332. => yolov3/yolo-v3/Conv_15/BatchNorm/gamma             (128,)
333. => yolov3/yolo-v3/Conv_15/BatchNorm/beta              (128,)
334. => yolov3/yolo-v3/Conv_15/BatchNorm/moving_mean       (128,)
335. => yolov3/yolo-v3/Conv_15/BatchNorm/moving_variance   (128,)
336. => yolov3/yolo-v3/Conv_16/weights                     (1, 1, 384, 128)
337. => yolov3/yolo-v3/Conv_16/BatchNorm/gamma             (128,)
338. => yolov3/yolo-v3/Conv_16/BatchNorm/beta              (128,)
339. => yolov3/yolo-v3/Conv_16/BatchNorm/moving_mean       (128,)
340. => yolov3/yolo-v3/Conv_16/BatchNorm/moving_variance   (128,)
341. => yolov3/yolo-v3/Conv_17/weights                     (3, 3, 128, 256)
342. => yolov3/yolo-v3/Conv_17/BatchNorm/gamma             (256,)
343. => yolov3/yolo-v3/Conv_17/BatchNorm/beta              (256,)
344. => yolov3/yolo-v3/Conv_17/BatchNorm/moving_mean       (256,)
345. => yolov3/yolo-v3/Conv_17/BatchNorm/moving_variance   (256,)
346. => yolov3/yolo-v3/Conv_18/weights                     (1, 1, 256, 128)
347. => yolov3/yolo-v3/Conv_18/BatchNorm/gamma             (128,)
348. => yolov3/yolo-v3/Conv_18/BatchNorm/beta              (128,)
349. => yolov3/yolo-v3/Conv_18/BatchNorm/moving_mean       (128,)
350. => yolov3/yolo-v3/Conv_18/BatchNorm/moving_variance   (128,)
351. => yolov3/yolo-v3/Conv_19/weights                     (3, 3, 128, 256)
352. => yolov3/yolo-v3/Conv_19/BatchNorm/gamma             (256,)
353. => yolov3/yolo-v3/Conv_19/BatchNorm/beta              (256,)
354. => yolov3/yolo-v3/Conv_19/BatchNorm/moving_mean       (256,)
355. => yolov3/yolo-v3/Conv_19/BatchNorm/moving_variance   (256,)
356. => yolov3/yolo-v3/Conv_20/weights                     (1, 1, 256, 128)
357. => yolov3/yolo-v3/Conv_20/BatchNorm/gamma             (128,)
358. => yolov3/yolo-v3/Conv_20/BatchNorm/beta              (128,)
359. => yolov3/yolo-v3/Conv_20/BatchNorm/moving_mean       (128,)
360. => yolov3/yolo-v3/Conv_20/BatchNorm/moving_variance   (128,)
361. => yolov3/yolo-v3/Conv_21/weights                     (3, 3, 128, 256)
362. => yolov3/yolo-v3/Conv_21/BatchNorm/gamma             (256,)
363. => yolov3/yolo-v3/Conv_21/BatchNorm/beta              (256,)
364. => yolov3/yolo-v3/Conv_21/BatchNorm/moving_mean       (256,)
365. => yolov3/yolo-v3/Conv_21/BatchNorm/moving_variance   (256,)
366. => yolov3/yolo-v3/Conv_22/weights                     (1, 1, 256, 255)
367. => yolov3/yolo-v3/Conv_22/biases                      (255,)
368.

 

Tensor("conv_sbbox/BiasAdd:0", shape=(?, ?, ?, 255), dtype=float32) Tensor("conv_mbbox/BiasAdd:0", shape=(?, ?, ?, 255), dtype=float32) Tensor("conv_lbbox/BiasAdd:0", shape=(?, ?, ?, 255), dtype=float32)

 

 

相关文章
|
20天前
|
监控 算法 数据安全/隐私保护
基于三帧差算法的运动目标检测系统FPGA实现,包含testbench和MATLAB辅助验证程序
本项目展示了基于FPGA与MATLAB实现的三帧差算法运动目标检测。使用Vivado 2019.2和MATLAB 2022a开发环境,通过对比连续三帧图像的像素值变化,有效识别运动区域。项目包括完整无水印的运行效果预览、详细中文注释的代码及操作步骤视频,适合学习和研究。
|
25天前
|
JSON 算法 数据可视化
测试专项笔记(一): 通过算法能力接口返回的检测结果完成相关指标的计算(目标检测)
这篇文章是关于如何通过算法接口返回的目标检测结果来计算性能指标的笔记。它涵盖了任务描述、指标分析(包括TP、FP、FN、TN、精准率和召回率),接口处理,数据集处理,以及如何使用实用工具进行文件操作和数据可视化。文章还提供了一些Python代码示例,用于处理图像文件、转换数据格式以及计算目标检测的性能指标。
46 0
测试专项笔记(一): 通过算法能力接口返回的检测结果完成相关指标的计算(目标检测)
|
3月前
|
机器学习/深度学习 人工智能 PyTorch
AI智能体研发之路-模型篇(五):pytorch vs tensorflow框架DNN网络结构源码级对比
AI智能体研发之路-模型篇(五):pytorch vs tensorflow框架DNN网络结构源码级对比
76 1
|
3月前
|
测试技术 数据库
探索JSF单元测试秘籍!如何让您的应用更稳固、更高效?揭秘成功背后的测试之道!
【8月更文挑战第31天】在 JavaServer Faces(JSF)应用开发中,确保代码质量和可维护性至关重要。本文详细介绍了如何通过单元测试实现这一目标。首先,阐述了单元测试的重要性及其对应用稳定性的影响;其次,提出了提高 JSF 应用可测试性的设计建议,如避免直接访问外部资源和使用依赖注入;最后,通过一个具体的 `UserBean` 示例,展示了如何利用 JUnit 和 Mockito 框架编写有效的单元测试。通过这些方法,不仅能够确保代码质量,还能提高开发效率和降低维护成本。
49 0
|
3月前
|
UED 开发者
哇塞!Uno Platform 数据绑定超全技巧大揭秘!从基础绑定到高级转换,优化性能让你的开发如虎添翼
【8月更文挑战第31天】在开发过程中,数据绑定是连接数据模型与用户界面的关键环节,可实现数据自动更新。Uno Platform 提供了简洁高效的数据绑定方式,使属性变化时 UI 自动同步更新。通过示例展示了基本绑定方法及使用 `Converter` 转换数据的高级技巧,如将年龄转换为格式化字符串。此外,还可利用 `BindingMode.OneTime` 提升性能。掌握这些技巧能显著提高开发效率并优化用户体验。
59 0
|
3月前
|
UED 开发工具 iOS开发
Uno Platform大揭秘:如何在你的跨平台应用中,巧妙融入第三方库与服务,一键解锁无限可能,让应用功能飙升,用户体验爆棚!
【8月更文挑战第31天】Uno Platform 让开发者能用同一代码库打造 Windows、iOS、Android、macOS 甚至 Web 的多彩应用。本文介绍如何在 Uno Platform 中集成第三方库和服务,如 Mapbox 或 Google Maps 的 .NET SDK,以增强应用功能并提升用户体验。通过 NuGet 安装所需库,并在 XAML 页面中添加相应控件,即可实现地图等功能。尽管 Uno 平台减少了平台差异,但仍需关注版本兼容性和性能问题,确保应用在多平台上表现一致。掌握正确方法,让跨平台应用更出色。
47 0
|
4月前
|
监控 算法 自动驾驶
目标检测算法:从理论到实践的深度探索
【7月更文第18天】目标检测,作为计算机视觉领域的核心任务之一,旨在识别图像或视频中特定对象的位置及其类别。这一技术在自动驾驶、视频监控、医疗影像分析等多个领域发挥着至关重要的作用。本文将深入浅出地介绍目标检测的基本概念、主流算法,并通过一个实际的代码示例,带您领略YOLOv5这一高效目标检测模型的魅力。
548 11
|
4月前
|
机器学习/深度学习 人工智能 监控
人工智能 - 目标检测算法详解及实战
目标检测需识别目标类别与位置,核心挑战为复杂背景下的多目标精准快速检测。算法分两步:目标提取(滑动窗口或区域提议)和分类(常用CNN)。IoU衡量预测与真实框重叠度,越接近1,检测越准。主流算法包括R-CNN系列(R-CNN, Fast R-CNN, Faster R-CNN),YOLO系列,SSD,各具特色,如Faster R-CNN高效候选区生成与检测,YOLO适用于实时应用。应用场景丰富,如自动驾驶行人车辆检测,安防监控,智能零售商品识别等。实现涉及数据准备、模型训练(示例YOLOv3)、评估(Precision, Recall, mAP)及测试。
132 5
|
15天前
|
算法 安全 数据安全/隐私保护
基于game-based算法的动态频谱访问matlab仿真
本算法展示了在认知无线电网络中,通过游戏理论优化动态频谱访问,提高频谱利用率和物理层安全性。程序运行效果包括负载因子、传输功率、信噪比对用户效用和保密率的影响分析。软件版本:Matlab 2022a。完整代码包含详细中文注释和操作视频。
|
1天前
|
算法 调度
基于遗传模拟退火混合优化算法的车间作业最优调度matlab仿真,输出甘特图
车间作业调度问题(JSSP)通过遗传算法(GA)和模拟退火算法(SA)优化多个作业在并行工作中心上的加工顺序和时间,以最小化总完成时间和机器闲置时间。MATLAB2022a版本运行测试,展示了有效性和可行性。核心程序采用作业列表表示法,结合遗传操作和模拟退火过程,提高算法性能。