AI 助理
备案控制台
开发者社区 人工智能 文章 正文

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

2021-11-05 211
版权
版权声明：
本文内容由阿里云实名注册用户自发贡献，版权归原作者所有，阿里云开发者社区不拥有其著作权，亦不承担相应法律责任。具体规则请查看《 阿里云开发者社区用户服务协议》和 《阿里云开发者社区知识产权保护指引》。如果您发现本社区中有涉嫌抄袭的内容，填写 侵权投诉表单进行举报，一经查实，本社区将立刻删除涉嫌侵权内容。
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

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

image.png

image.png

image.png



2019-12-25 15:05:02.766745: I

=> yolov3/darknet-53/Conv/weights                     (3, 3, 3, 32)

=> yolov3/darknet-53/Conv/BatchNorm/gamma             (32,)

=> yolov3/darknet-53/Conv/BatchNorm/beta              (32,)

=> yolov3/darknet-53/Conv/BatchNorm/moving_mean       (32,)

=> yolov3/darknet-53/Conv/BatchNorm/moving_variance   (32,)

=> yolov3/darknet-53/Conv_1/weights                   (3, 3, 32, 64)

=> yolov3/darknet-53/Conv_1/BatchNorm/gamma           (64,)

=> yolov3/darknet-53/Conv_1/BatchNorm/beta            (64,)

=> yolov3/darknet-53/Conv_1/BatchNorm/moving_mean     (64,)

=> yolov3/darknet-53/Conv_1/BatchNorm/moving_variance (64,)

=> yolov3/darknet-53/Conv_2/weights                   (1, 1, 64, 32)

=> yolov3/darknet-53/Conv_2/BatchNorm/gamma           (32,)

=> yolov3/darknet-53/Conv_2/BatchNorm/beta            (32,)

=> yolov3/darknet-53/Conv_2/BatchNorm/moving_mean     (32,)

=> yolov3/darknet-53/Conv_2/BatchNorm/moving_variance (32,)

=> yolov3/darknet-53/Conv_3/weights                   (3, 3, 32, 64)

=> yolov3/darknet-53/Conv_3/BatchNorm/gamma           (64,)

=> yolov3/darknet-53/Conv_3/BatchNorm/beta            (64,)

=> yolov3/darknet-53/Conv_3/BatchNorm/moving_mean     (64,)

=> yolov3/darknet-53/Conv_3/BatchNorm/moving_variance (64,)

=> yolov3/darknet-53/Conv_4/weights                   (3, 3, 64, 128)

=> yolov3/darknet-53/Conv_4/BatchNorm/gamma           (128,)

=> yolov3/darknet-53/Conv_4/BatchNorm/beta            (128,)

=> yolov3/darknet-53/Conv_4/BatchNorm/moving_mean     (128,)

=> yolov3/darknet-53/Conv_4/BatchNorm/moving_variance (128,)

=> yolov3/darknet-53/Conv_5/weights                   (1, 1, 128, 64)

=> yolov3/darknet-53/Conv_5/BatchNorm/gamma           (64,)

=> yolov3/darknet-53/Conv_5/BatchNorm/beta            (64,)

=> yolov3/darknet-53/Conv_5/BatchNorm/moving_mean     (64,)

=> yolov3/darknet-53/Conv_5/BatchNorm/moving_variance (64,)

=> yolov3/darknet-53/Conv_6/weights                   (3, 3, 64, 128)

=> yolov3/darknet-53/Conv_6/BatchNorm/gamma           (128,)

=> yolov3/darknet-53/Conv_6/BatchNorm/beta            (128,)

=> yolov3/darknet-53/Conv_6/BatchNorm/moving_mean     (128,)

=> yolov3/darknet-53/Conv_6/BatchNorm/moving_variance (128,)

=> yolov3/darknet-53/Conv_7/weights                   (1, 1, 128, 64)

=> yolov3/darknet-53/Conv_7/BatchNorm/gamma           (64,)

=> yolov3/darknet-53/Conv_7/BatchNorm/beta            (64,)

=> yolov3/darknet-53/Conv_7/BatchNorm/moving_mean     (64,)

=> yolov3/darknet-53/Conv_7/BatchNorm/moving_variance (64,)

=> yolov3/darknet-53/Conv_8/weights                   (3, 3, 64, 128)

=> yolov3/darknet-53/Conv_8/BatchNorm/gamma           (128,)

=> yolov3/darknet-53/Conv_8/BatchNorm/beta            (128,)

=> yolov3/darknet-53/Conv_8/BatchNorm/moving_mean     (128,)

=> yolov3/darknet-53/Conv_8/BatchNorm/moving_variance (128,)

=> yolov3/darknet-53/Conv_9/weights                   (3, 3, 128, 256)

=> yolov3/darknet-53/Conv_9/BatchNorm/gamma           (256,)

=> yolov3/darknet-53/Conv_9/BatchNorm/beta            (256,)

=> yolov3/darknet-53/Conv_9/BatchNorm/moving_mean     (256,)

=> yolov3/darknet-53/Conv_9/BatchNorm/moving_variance (256,)

=> yolov3/darknet-53/Conv_10/weights                  (1, 1, 256, 128)

=> yolov3/darknet-53/Conv_10/BatchNorm/gamma          (128,)

=> yolov3/darknet-53/Conv_10/BatchNorm/beta           (128,)

=> yolov3/darknet-53/Conv_10/BatchNorm/moving_mean    (128,)

=> yolov3/darknet-53/Conv_10/BatchNorm/moving_variance (128,)

=> yolov3/darknet-53/Conv_11/weights                  (3, 3, 128, 256)

=> yolov3/darknet-53/Conv_11/BatchNorm/gamma          (256,)

=> yolov3/darknet-53/Conv_11/BatchNorm/beta           (256,)

=> yolov3/darknet-53/Conv_11/BatchNorm/moving_mean    (256,)

=> yolov3/darknet-53/Conv_11/BatchNorm/moving_variance (256,)

=> yolov3/darknet-53/Conv_12/weights                  (1, 1, 256, 128)

=> yolov3/darknet-53/Conv_12/BatchNorm/gamma          (128,)

=> yolov3/darknet-53/Conv_12/BatchNorm/beta           (128,)

=> yolov3/darknet-53/Conv_12/BatchNorm/moving_mean    (128,)

=> yolov3/darknet-53/Conv_12/BatchNorm/moving_variance (128,)

=> yolov3/darknet-53/Conv_13/weights                  (3, 3, 128, 256)

=> yolov3/darknet-53/Conv_13/BatchNorm/gamma          (256,)

=> yolov3/darknet-53/Conv_13/BatchNorm/beta           (256,)

=> yolov3/darknet-53/Conv_13/BatchNorm/moving_mean    (256,)

=> yolov3/darknet-53/Conv_13/BatchNorm/moving_variance (256,)

=> yolov3/darknet-53/Conv_14/weights                  (1, 1, 256, 128)

=> yolov3/darknet-53/Conv_14/BatchNorm/gamma          (128,)

=> yolov3/darknet-53/Conv_14/BatchNorm/beta           (128,)

=> yolov3/darknet-53/Conv_14/BatchNorm/moving_mean    (128,)

=> yolov3/darknet-53/Conv_14/BatchNorm/moving_variance (128,)

=> yolov3/darknet-53/Conv_15/weights                  (3, 3, 128, 256)

=> yolov3/darknet-53/Conv_15/BatchNorm/gamma          (256,)

=> yolov3/darknet-53/Conv_15/BatchNorm/beta           (256,)

=> yolov3/darknet-53/Conv_15/BatchNorm/moving_mean    (256,)

=> yolov3/darknet-53/Conv_15/BatchNorm/moving_variance (256,)

=> yolov3/darknet-53/Conv_16/weights                  (1, 1, 256, 128)

=> yolov3/darknet-53/Conv_16/BatchNorm/gamma          (128,)

=> yolov3/darknet-53/Conv_16/BatchNorm/beta           (128,)

=> yolov3/darknet-53/Conv_16/BatchNorm/moving_mean    (128,)

=> yolov3/darknet-53/Conv_16/BatchNorm/moving_variance (128,)

=> yolov3/darknet-53/Conv_17/weights                  (3, 3, 128, 256)

=> yolov3/darknet-53/Conv_17/BatchNorm/gamma          (256,)

=> yolov3/darknet-53/Conv_17/BatchNorm/beta           (256,)

=> yolov3/darknet-53/Conv_17/BatchNorm/moving_mean    (256,)

=> yolov3/darknet-53/Conv_17/BatchNorm/moving_variance (256,)

=> yolov3/darknet-53/Conv_18/weights                  (1, 1, 256, 128)

=> yolov3/darknet-53/Conv_18/BatchNorm/gamma          (128,)

=> yolov3/darknet-53/Conv_18/BatchNorm/beta           (128,)

=> yolov3/darknet-53/Conv_18/BatchNorm/moving_mean    (128,)

=> yolov3/darknet-53/Conv_18/BatchNorm/moving_variance (128,)

=> yolov3/darknet-53/Conv_19/weights                  (3, 3, 128, 256)

=> yolov3/darknet-53/Conv_19/BatchNorm/gamma          (256,)

=> yolov3/darknet-53/Conv_19/BatchNorm/beta           (256,)

=> yolov3/darknet-53/Conv_19/BatchNorm/moving_mean    (256,)

=> yolov3/darknet-53/Conv_19/BatchNorm/moving_variance (256,)

=> yolov3/darknet-53/Conv_20/weights                  (1, 1, 256, 128)

=> yolov3/darknet-53/Conv_20/BatchNorm/gamma          (128,)

=> yolov3/darknet-53/Conv_20/BatchNorm/beta           (128,)

=> yolov3/darknet-53/Conv_20/BatchNorm/moving_mean    (128,)

=> yolov3/darknet-53/Conv_20/BatchNorm/moving_variance (128,)

=> yolov3/darknet-53/Conv_21/weights                  (3, 3, 128, 256)

=> yolov3/darknet-53/Conv_21/BatchNorm/gamma          (256,)

=> yolov3/darknet-53/Conv_21/BatchNorm/beta           (256,)

=> yolov3/darknet-53/Conv_21/BatchNorm/moving_mean    (256,)

=> yolov3/darknet-53/Conv_21/BatchNorm/moving_variance (256,)

=> yolov3/darknet-53/Conv_22/weights                  (1, 1, 256, 128)

=> yolov3/darknet-53/Conv_22/BatchNorm/gamma          (128,)

=> yolov3/darknet-53/Conv_22/BatchNorm/beta           (128,)

=> yolov3/darknet-53/Conv_22/BatchNorm/moving_mean    (128,)

=> yolov3/darknet-53/Conv_22/BatchNorm/moving_variance (128,)

=> yolov3/darknet-53/Conv_23/weights                  (3, 3, 128, 256)

=> yolov3/darknet-53/Conv_23/BatchNorm/gamma          (256,)

=> yolov3/darknet-53/Conv_23/BatchNorm/beta           (256,)

=> yolov3/darknet-53/Conv_23/BatchNorm/moving_mean    (256,)

=> yolov3/darknet-53/Conv_23/BatchNorm/moving_variance (256,)

=> yolov3/darknet-53/Conv_24/weights                  (1, 1, 256, 128)

=> yolov3/darknet-53/Conv_24/BatchNorm/gamma          (128,)

=> yolov3/darknet-53/Conv_24/BatchNorm/beta           (128,)

=> yolov3/darknet-53/Conv_24/BatchNorm/moving_mean    (128,)

=> yolov3/darknet-53/Conv_24/BatchNorm/moving_variance (128,)

=> yolov3/darknet-53/Conv_25/weights                  (3, 3, 128, 256)

=> yolov3/darknet-53/Conv_25/BatchNorm/gamma          (256,)

=> yolov3/darknet-53/Conv_25/BatchNorm/beta           (256,)

=> yolov3/darknet-53/Conv_25/BatchNorm/moving_mean    (256,)

=> yolov3/darknet-53/Conv_25/BatchNorm/moving_variance (256,)

=> yolov3/darknet-53/Conv_26/weights                  (3, 3, 256, 512)

=> yolov3/darknet-53/Conv_26/BatchNorm/gamma          (512,)

=> yolov3/darknet-53/Conv_26/BatchNorm/beta           (512,)

=> yolov3/darknet-53/Conv_26/BatchNorm/moving_mean    (512,)

=> yolov3/darknet-53/Conv_26/BatchNorm/moving_variance (512,)

=> yolov3/darknet-53/Conv_27/weights                  (1, 1, 512, 256)

=> yolov3/darknet-53/Conv_27/BatchNorm/gamma          (256,)

=> yolov3/darknet-53/Conv_27/BatchNorm/beta           (256,)

=> yolov3/darknet-53/Conv_27/BatchNorm/moving_mean    (256,)

=> yolov3/darknet-53/Conv_27/BatchNorm/moving_variance (256,)

=> yolov3/darknet-53/Conv_28/weights                  (3, 3, 256, 512)

=> yolov3/darknet-53/Conv_28/BatchNorm/gamma          (512,)

=> yolov3/darknet-53/Conv_28/BatchNorm/beta           (512,)

=> yolov3/darknet-53/Conv_28/BatchNorm/moving_mean    (512,)

=> yolov3/darknet-53/Conv_28/BatchNorm/moving_variance (512,)

=> yolov3/darknet-53/Conv_29/weights                  (1, 1, 512, 256)

=> yolov3/darknet-53/Conv_29/BatchNorm/gamma          (256,)

=> yolov3/darknet-53/Conv_29/BatchNorm/beta           (256,)

=> yolov3/darknet-53/Conv_29/BatchNorm/moving_mean    (256,)

=> yolov3/darknet-53/Conv_29/BatchNorm/moving_variance (256,)

=> yolov3/darknet-53/Conv_30/weights                  (3, 3, 256, 512)

=> yolov3/darknet-53/Conv_30/BatchNorm/gamma          (512,)

=> yolov3/darknet-53/Conv_30/BatchNorm/beta           (512,)

=> yolov3/darknet-53/Conv_30/BatchNorm/moving_mean    (512,)

=> yolov3/darknet-53/Conv_30/BatchNorm/moving_variance (512,)

=> yolov3/darknet-53/Conv_31/weights                  (1, 1, 512, 256)

=> yolov3/darknet-53/Conv_31/BatchNorm/gamma          (256,)

=> yolov3/darknet-53/Conv_31/BatchNorm/beta           (256,)

=> yolov3/darknet-53/Conv_31/BatchNorm/moving_mean    (256,)

=> yolov3/darknet-53/Conv_31/BatchNorm/moving_variance (256,)

=> yolov3/darknet-53/Conv_32/weights                  (3, 3, 256, 512)

=> yolov3/darknet-53/Conv_32/BatchNorm/gamma          (512,)

=> yolov3/darknet-53/Conv_32/BatchNorm/beta           (512,)

=> yolov3/darknet-53/Conv_32/BatchNorm/moving_mean    (512,)

=> yolov3/darknet-53/Conv_32/BatchNorm/moving_variance (512,)

=> yolov3/darknet-53/Conv_33/weights                  (1, 1, 512, 256)

=> yolov3/darknet-53/Conv_33/BatchNorm/gamma          (256,)

=> yolov3/darknet-53/Conv_33/BatchNorm/beta           (256,)

=> yolov3/darknet-53/Conv_33/BatchNorm/moving_mean    (256,)

=> yolov3/darknet-53/Conv_33/BatchNorm/moving_variance (256,)

=> yolov3/darknet-53/Conv_34/weights                  (3, 3, 256, 512)

=> yolov3/darknet-53/Conv_34/BatchNorm/gamma          (512,)

=> yolov3/darknet-53/Conv_34/BatchNorm/beta           (512,)

=> yolov3/darknet-53/Conv_34/BatchNorm/moving_mean    (512,)

=> yolov3/darknet-53/Conv_34/BatchNorm/moving_variance (512,)

=> yolov3/darknet-53/Conv_35/weights                  (1, 1, 512, 256)

=> yolov3/darknet-53/Conv_35/BatchNorm/gamma          (256,)

=> yolov3/darknet-53/Conv_35/BatchNorm/beta           (256,)

=> yolov3/darknet-53/Conv_35/BatchNorm/moving_mean    (256,)

=> yolov3/darknet-53/Conv_35/BatchNorm/moving_variance (256,)

=> yolov3/darknet-53/Conv_36/weights                  (3, 3, 256, 512)

=> yolov3/darknet-53/Conv_36/BatchNorm/gamma          (512,)

=> yolov3/darknet-53/Conv_36/BatchNorm/beta           (512,)

=> yolov3/darknet-53/Conv_36/BatchNorm/moving_mean    (512,)

=> yolov3/darknet-53/Conv_36/BatchNorm/moving_variance (512,)

=> yolov3/darknet-53/Conv_37/weights                  (1, 1, 512, 256)

=> yolov3/darknet-53/Conv_37/BatchNorm/gamma          (256,)

=> yolov3/darknet-53/Conv_37/BatchNorm/beta           (256,)

=> yolov3/darknet-53/Conv_37/BatchNorm/moving_mean    (256,)

=> yolov3/darknet-53/Conv_37/BatchNorm/moving_variance (256,)

=> yolov3/darknet-53/Conv_38/weights                  (3, 3, 256, 512)

=> yolov3/darknet-53/Conv_38/BatchNorm/gamma          (512,)

=> yolov3/darknet-53/Conv_38/BatchNorm/beta           (512,)

=> yolov3/darknet-53/Conv_38/BatchNorm/moving_mean    (512,)

=> yolov3/darknet-53/Conv_38/BatchNorm/moving_variance (512,)

=> yolov3/darknet-53/Conv_39/weights                  (1, 1, 512, 256)

=> yolov3/darknet-53/Conv_39/BatchNorm/gamma          (256,)

=> yolov3/darknet-53/Conv_39/BatchNorm/beta           (256,)

=> yolov3/darknet-53/Conv_39/BatchNorm/moving_mean    (256,)

=> yolov3/darknet-53/Conv_39/BatchNorm/moving_variance (256,)

=> yolov3/darknet-53/Conv_40/weights                  (3, 3, 256, 512)

=> yolov3/darknet-53/Conv_40/BatchNorm/gamma          (512,)

=> yolov3/darknet-53/Conv_40/BatchNorm/beta           (512,)

=> yolov3/darknet-53/Conv_40/BatchNorm/moving_mean    (512,)

=> yolov3/darknet-53/Conv_40/BatchNorm/moving_variance (512,)

=> yolov3/darknet-53/Conv_41/weights                  (1, 1, 512, 256)

=> yolov3/darknet-53/Conv_41/BatchNorm/gamma          (256,)

=> yolov3/darknet-53/Conv_41/BatchNorm/beta           (256,)

=> yolov3/darknet-53/Conv_41/BatchNorm/moving_mean    (256,)

=> yolov3/darknet-53/Conv_41/BatchNorm/moving_variance (256,)

=> yolov3/darknet-53/Conv_42/weights                  (3, 3, 256, 512)

=> yolov3/darknet-53/Conv_42/BatchNorm/gamma          (512,)

=> yolov3/darknet-53/Conv_42/BatchNorm/beta           (512,)

=> yolov3/darknet-53/Conv_42/BatchNorm/moving_mean    (512,)

=> yolov3/darknet-53/Conv_42/BatchNorm/moving_variance (512,)

=> yolov3/darknet-53/Conv_43/weights                  (3, 3, 512, 1024)

=> yolov3/darknet-53/Conv_43/BatchNorm/gamma          (1024,)

=> yolov3/darknet-53/Conv_43/BatchNorm/beta           (1024,)

=> yolov3/darknet-53/Conv_43/BatchNorm/moving_mean    (1024,)

=> yolov3/darknet-53/Conv_43/BatchNorm/moving_variance (1024,)

=> yolov3/darknet-53/Conv_44/weights                  (1, 1, 1024, 512)

=> yolov3/darknet-53/Conv_44/BatchNorm/gamma          (512,)

=> yolov3/darknet-53/Conv_44/BatchNorm/beta           (512,)

=> yolov3/darknet-53/Conv_44/BatchNorm/moving_mean    (512,)

=> yolov3/darknet-53/Conv_44/BatchNorm/moving_variance (512,)

=> yolov3/darknet-53/Conv_45/weights                  (3, 3, 512, 1024)

=> yolov3/darknet-53/Conv_45/BatchNorm/gamma          (1024,)

=> yolov3/darknet-53/Conv_45/BatchNorm/beta           (1024,)

=> yolov3/darknet-53/Conv_45/BatchNorm/moving_mean    (1024,)

=> yolov3/darknet-53/Conv_45/BatchNorm/moving_variance (1024,)

=> yolov3/darknet-53/Conv_46/weights                  (1, 1, 1024, 512)

=> yolov3/darknet-53/Conv_46/BatchNorm/gamma          (512,)

=> yolov3/darknet-53/Conv_46/BatchNorm/beta           (512,)

=> yolov3/darknet-53/Conv_46/BatchNorm/moving_mean    (512,)

=> yolov3/darknet-53/Conv_46/BatchNorm/moving_variance (512,)

=> yolov3/darknet-53/Conv_47/weights                  (3, 3, 512, 1024)

=> yolov3/darknet-53/Conv_47/BatchNorm/gamma          (1024,)

=> yolov3/darknet-53/Conv_47/BatchNorm/beta           (1024,)

=> yolov3/darknet-53/Conv_47/BatchNorm/moving_mean    (1024,)

=> yolov3/darknet-53/Conv_47/BatchNorm/moving_variance (1024,)

=> yolov3/darknet-53/Conv_48/weights                  (1, 1, 1024, 512)

=> yolov3/darknet-53/Conv_48/BatchNorm/gamma          (512,)

=> yolov3/darknet-53/Conv_48/BatchNorm/beta           (512,)

=> yolov3/darknet-53/Conv_48/BatchNorm/moving_mean    (512,)

=> yolov3/darknet-53/Conv_48/BatchNorm/moving_variance (512,)

=> yolov3/darknet-53/Conv_49/weights                  (3, 3, 512, 1024)

=> yolov3/darknet-53/Conv_49/BatchNorm/gamma          (1024,)

=> yolov3/darknet-53/Conv_49/BatchNorm/beta           (1024,)

=> yolov3/darknet-53/Conv_49/BatchNorm/moving_mean    (1024,)

=> yolov3/darknet-53/Conv_49/BatchNorm/moving_variance (1024,)

=> yolov3/darknet-53/Conv_50/weights                  (1, 1, 1024, 512)

=> yolov3/darknet-53/Conv_50/BatchNorm/gamma          (512,)

=> yolov3/darknet-53/Conv_50/BatchNorm/beta           (512,)

=> yolov3/darknet-53/Conv_50/BatchNorm/moving_mean    (512,)

=> yolov3/darknet-53/Conv_50/BatchNorm/moving_variance (512,)

=> yolov3/darknet-53/Conv_51/weights                  (3, 3, 512, 1024)

=> yolov3/darknet-53/Conv_51/BatchNorm/gamma          (1024,)

=> yolov3/darknet-53/Conv_51/BatchNorm/beta           (1024,)

=> yolov3/darknet-53/Conv_51/BatchNorm/moving_mean    (1024,)

=> yolov3/darknet-53/Conv_51/BatchNorm/moving_variance (1024,)

=> yolov3/yolo-v3/Conv/weights                        (1, 1, 1024, 512)

=> yolov3/yolo-v3/Conv/BatchNorm/gamma                (512,)

=> yolov3/yolo-v3/Conv/BatchNorm/beta                 (512,)

=> yolov3/yolo-v3/Conv/BatchNorm/moving_mean          (512,)

=> yolov3/yolo-v3/Conv/BatchNorm/moving_variance      (512,)

=> yolov3/yolo-v3/Conv_1/weights                      (3, 3, 512, 1024)

=> yolov3/yolo-v3/Conv_1/BatchNorm/gamma              (1024,)

=> yolov3/yolo-v3/Conv_1/BatchNorm/beta               (1024,)

=> yolov3/yolo-v3/Conv_1/BatchNorm/moving_mean        (1024,)

=> yolov3/yolo-v3/Conv_1/BatchNorm/moving_variance    (1024,)

=> yolov3/yolo-v3/Conv_2/weights                      (1, 1, 1024, 512)

=> yolov3/yolo-v3/Conv_2/BatchNorm/gamma              (512,)

=> yolov3/yolo-v3/Conv_2/BatchNorm/beta               (512,)

=> yolov3/yolo-v3/Conv_2/BatchNorm/moving_mean        (512,)

=> yolov3/yolo-v3/Conv_2/BatchNorm/moving_variance    (512,)

=> yolov3/yolo-v3/Conv_3/weights                      (3, 3, 512, 1024)

=> yolov3/yolo-v3/Conv_3/BatchNorm/gamma              (1024,)

=> yolov3/yolo-v3/Conv_3/BatchNorm/beta               (1024,)

=> yolov3/yolo-v3/Conv_3/BatchNorm/moving_mean        (1024,)

=> yolov3/yolo-v3/Conv_3/BatchNorm/moving_variance    (1024,)

=> yolov3/yolo-v3/Conv_4/weights                      (1, 1, 1024, 512)

=> yolov3/yolo-v3/Conv_4/BatchNorm/gamma              (512,)

=> yolov3/yolo-v3/Conv_4/BatchNorm/beta               (512,)

=> yolov3/yolo-v3/Conv_4/BatchNorm/moving_mean        (512,)

=> yolov3/yolo-v3/Conv_4/BatchNorm/moving_variance    (512,)

=> yolov3/yolo-v3/Conv_5/weights                      (3, 3, 512, 1024)

=> yolov3/yolo-v3/Conv_5/BatchNorm/gamma              (1024,)

=> yolov3/yolo-v3/Conv_5/BatchNorm/beta               (1024,)

=> yolov3/yolo-v3/Conv_5/BatchNorm/moving_mean        (1024,)

=> yolov3/yolo-v3/Conv_5/BatchNorm/moving_variance    (1024,)

=> yolov3/yolo-v3/Conv_6/weights                      (1, 1, 1024, 255)

=> yolov3/yolo-v3/Conv_6/biases                       (255,)

=> yolov3/yolo-v3/Conv_7/weights                      (1, 1, 512, 256)

=> yolov3/yolo-v3/Conv_7/BatchNorm/gamma              (256,)

=> yolov3/yolo-v3/Conv_7/BatchNorm/beta               (256,)

=> yolov3/yolo-v3/Conv_7/BatchNorm/moving_mean        (256,)

=> yolov3/yolo-v3/Conv_7/BatchNorm/moving_variance    (256,)

=> yolov3/yolo-v3/Conv_8/weights                      (1, 1, 768, 256)

=> yolov3/yolo-v3/Conv_8/BatchNorm/gamma              (256,)

=> yolov3/yolo-v3/Conv_8/BatchNorm/beta               (256,)

=> yolov3/yolo-v3/Conv_8/BatchNorm/moving_mean        (256,)

=> yolov3/yolo-v3/Conv_8/BatchNorm/moving_variance    (256,)

=> yolov3/yolo-v3/Conv_9/weights                      (3, 3, 256, 512)

=> yolov3/yolo-v3/Conv_9/BatchNorm/gamma              (512,)

=> yolov3/yolo-v3/Conv_9/BatchNorm/beta               (512,)

=> yolov3/yolo-v3/Conv_9/BatchNorm/moving_mean        (512,)

=> yolov3/yolo-v3/Conv_9/BatchNorm/moving_variance    (512,)

=> yolov3/yolo-v3/Conv_10/weights                     (1, 1, 512, 256)

=> yolov3/yolo-v3/Conv_10/BatchNorm/gamma             (256,)

=> yolov3/yolo-v3/Conv_10/BatchNorm/beta              (256,)

=> yolov3/yolo-v3/Conv_10/BatchNorm/moving_mean       (256,)

=> yolov3/yolo-v3/Conv_10/BatchNorm/moving_variance   (256,)

=> yolov3/yolo-v3/Conv_11/weights                     (3, 3, 256, 512)

=> yolov3/yolo-v3/Conv_11/BatchNorm/gamma             (512,)

=> yolov3/yolo-v3/Conv_11/BatchNorm/beta              (512,)

=> yolov3/yolo-v3/Conv_11/BatchNorm/moving_mean       (512,)

=> yolov3/yolo-v3/Conv_11/BatchNorm/moving_variance   (512,)

=> yolov3/yolo-v3/Conv_12/weights                     (1, 1, 512, 256)

=> yolov3/yolo-v3/Conv_12/BatchNorm/gamma             (256,)

=> yolov3/yolo-v3/Conv_12/BatchNorm/beta              (256,)

=> yolov3/yolo-v3/Conv_12/BatchNorm/moving_mean       (256,)

=> yolov3/yolo-v3/Conv_12/BatchNorm/moving_variance   (256,)

=> yolov3/yolo-v3/Conv_13/weights                     (3, 3, 256, 512)

=> yolov3/yolo-v3/Conv_13/BatchNorm/gamma             (512,)

=> yolov3/yolo-v3/Conv_13/BatchNorm/beta              (512,)

=> yolov3/yolo-v3/Conv_13/BatchNorm/moving_mean       (512,)

=> yolov3/yolo-v3/Conv_13/BatchNorm/moving_variance   (512,)

=> yolov3/yolo-v3/Conv_14/weights                     (1, 1, 512, 255)

=> yolov3/yolo-v3/Conv_14/biases                      (255,)

=> yolov3/yolo-v3/Conv_15/weights                     (1, 1, 256, 128)

=> yolov3/yolo-v3/Conv_15/BatchNorm/gamma             (128,)

=> yolov3/yolo-v3/Conv_15/BatchNorm/beta              (128,)

=> yolov3/yolo-v3/Conv_15/BatchNorm/moving_mean       (128,)

=> yolov3/yolo-v3/Conv_15/BatchNorm/moving_variance   (128,)

=> yolov3/yolo-v3/Conv_16/weights                     (1, 1, 384, 128)

=> yolov3/yolo-v3/Conv_16/BatchNorm/gamma             (128,)

=> yolov3/yolo-v3/Conv_16/BatchNorm/beta              (128,)

=> yolov3/yolo-v3/Conv_16/BatchNorm/moving_mean       (128,)

=> yolov3/yolo-v3/Conv_16/BatchNorm/moving_variance   (128,)

=> yolov3/yolo-v3/Conv_17/weights                     (3, 3, 128, 256)

=> yolov3/yolo-v3/Conv_17/BatchNorm/gamma             (256,)

=> yolov3/yolo-v3/Conv_17/BatchNorm/beta              (256,)

=> yolov3/yolo-v3/Conv_17/BatchNorm/moving_mean       (256,)

=> yolov3/yolo-v3/Conv_17/BatchNorm/moving_variance   (256,)

=> yolov3/yolo-v3/Conv_18/weights                     (1, 1, 256, 128)

=> yolov3/yolo-v3/Conv_18/BatchNorm/gamma             (128,)

=> yolov3/yolo-v3/Conv_18/BatchNorm/beta              (128,)

=> yolov3/yolo-v3/Conv_18/BatchNorm/moving_mean       (128,)

=> yolov3/yolo-v3/Conv_18/BatchNorm/moving_variance   (128,)

=> yolov3/yolo-v3/Conv_19/weights                     (3, 3, 128, 256)

=> yolov3/yolo-v3/Conv_19/BatchNorm/gamma             (256,)

=> yolov3/yolo-v3/Conv_19/BatchNorm/beta              (256,)

=> yolov3/yolo-v3/Conv_19/BatchNorm/moving_mean       (256,)

=> yolov3/yolo-v3/Conv_19/BatchNorm/moving_variance   (256,)

=> yolov3/yolo-v3/Conv_20/weights                     (1, 1, 256, 128)

=> yolov3/yolo-v3/Conv_20/BatchNorm/gamma             (128,)

=> yolov3/yolo-v3/Conv_20/BatchNorm/beta              (128,)

=> yolov3/yolo-v3/Conv_20/BatchNorm/moving_mean       (128,)

=> yolov3/yolo-v3/Conv_20/BatchNorm/moving_variance   (128,)

=> yolov3/yolo-v3/Conv_21/weights                     (3, 3, 128, 256)

=> yolov3/yolo-v3/Conv_21/BatchNorm/gamma             (256,)

=> yolov3/yolo-v3/Conv_21/BatchNorm/beta              (256,)

=> yolov3/yolo-v3/Conv_21/BatchNorm/moving_mean       (256,)

=> yolov3/yolo-v3/Conv_21/BatchNorm/moving_variance   (256,)

=> yolov3/yolo-v3/Conv_22/weights                     (1, 1, 256, 255)

=> yolov3/yolo-v3/Conv_22/biases                      (255,)


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)



 


文章标签：
Python
计算机视觉
算法框架/工具
TensorFlow
算法
关键词：
cv算法
TensorFlow算法
算法tensorflow
算法框架
算法目标检测
一个处女座的程序猿
目录
相关文章
子午s
|
3月前
|
机器学习/深度学习 人工智能 算法
猫狗宠物识别系统Python+TensorFlow+人工智能+深度学习+卷积网络算法
宠物识别系统使用Python和TensorFlow搭建卷积神经网络，基于37种常见猫狗数据集训练高精度模型，并保存为h5格式。通过Django框架搭建Web平台，用户上传宠物图片即可识别其名称，提供便捷的宠物识别服务。
子午s
469 55
子午s
|
6月前
|
机器学习/深度学习 算法 TensorFlow
动物识别系统Python+卷积神经网络算法+TensorFlow+人工智能+图像识别+计算机毕业设计项目
动物识别系统。本项目以Python作为主要编程语言，并基于TensorFlow搭建ResNet50卷积神经网络算法模型，通过收集4种常见的动物图像数据集（猫、狗、鸡、马）然后进行模型训练，得到一个识别精度较高的模型文件，然后保存为本地格式的H5格式文件。再基于Django开发Web网页端操作界面，实现用户上传一张动物图片，识别其名称。
子午s
214 1
动物识别系统Python+卷积神经网络算法+TensorFlow+人工智能+图像识别+计算机毕业设计项目
子午s
|
3月前
|
机器学习/深度学习 人工智能 算法
【宠物识别系统】Python+卷积神经网络算法+深度学习+人工智能+TensorFlow+图像识别
宠物识别系统，本系统使用Python作为主要开发语言，基于TensorFlow搭建卷积神经网络算法，并收集了37种常见的猫狗宠物种类数据集【'阿比西尼亚猫（Abyssinian）', '孟加拉猫（Bengal）', '暹罗猫（Birman）', '孟买猫（Bombay）', '英国短毛猫（British Shorthair）', '埃及猫（Egyptian Mau）', '缅因猫（Maine Coon）', '波斯猫（Persian）', '布偶猫（Ragdoll）', '俄罗斯蓝猫（Russian Blue）', '暹罗猫（Siamese）', '斯芬克斯猫（Sphynx）', '美国斗牛犬
子午s
255 29
【宠物识别系统】Python+卷积神经网络算法+深度学习+人工智能+TensorFlow+图像识别
子午s
|
4月前
|
机器学习/深度学习 人工智能 算法
【车辆车型识别】Python+卷积神经网络算法+深度学习+人工智能+TensorFlow+算法模型
车辆车型识别，使用Python作为主要编程语言，通过收集多种车辆车型图像数据集，然后基于TensorFlow搭建卷积网络算法模型，并对数据集进行训练，最后得到一个识别精度较高的模型文件。再基于Django搭建web网页端操作界面，实现用户上传一张车辆图片识别其类型。
子午s
203 0
【车辆车型识别】Python+卷积神经网络算法+深度学习+人工智能+TensorFlow+算法模型
子午s
|
6月前
|
机器学习/深度学习 人工智能 算法
鸟类识别系统Python+卷积神经网络算法+深度学习+人工智能+TensorFlow+ResNet50算法模型+图像识别
鸟类识别系统。本系统采用Python作为主要开发语言，通过使用加利福利亚大学开源的200种鸟类图像作为数据集。使用TensorFlow搭建ResNet50卷积神经网络算法模型，然后进行模型的迭代训练，得到一个识别精度较高的模型，然后在保存为本地的H5格式文件。在使用Django开发Web网页端操作界面，实现用户上传一张鸟类图像，识别其名称。
子午s
198 12
鸟类识别系统Python+卷积神经网络算法+深度学习+人工智能+TensorFlow+ResNet50算法模型+图像识别
简简单单做算法
|
5月前
|
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。
简简单单做算法
129 2
子午s
|
6月前
|
机器学习/深度学习 算法 TensorFlow
交通标志识别系统Python+卷积神经网络算法+深度学习人工智能+TensorFlow模型训练+计算机课设项目+Django网页界面
交通标志识别系统。本系统使用Python作为主要编程语言，在交通标志图像识别功能实现中，基于TensorFlow搭建卷积神经网络算法模型，通过对收集到的58种常见的交通标志图像作为数据集，进行迭代训练最后得到一个识别精度较高的模型文件，然后保存为本地的h5格式文件。再使用Django开发Web网页端操作界面，实现用户上传一张交通标志图片，识别其名称。
子午s
288 6
交通标志识别系统Python+卷积神经网络算法+深度学习人工智能+TensorFlow模型训练+计算机课设项目+Django网页界面
子午s
|
5月前
|
机器学习/深度学习 人工智能 算法
【玉米病害识别】Python+卷积神经网络算法+人工智能+深度学习+计算机课设项目+TensorFlow+模型训练
玉米病害识别系统，本系统使用Python作为主要开发语言，通过收集了8种常见的玉米叶部病害图片数据集（'矮花叶病', '健康', '灰斑病一般', '灰斑病严重', '锈病一般', '锈病严重', '叶斑病一般', '叶斑病严重'），然后基于TensorFlow搭建卷积神经网络算法模型，通过对数据集进行多轮迭代训练，最后得到一个识别精度较高的模型文件。再使用Django搭建Web网页操作平台，实现用户上传一张玉米病害图片识别其名称。
子午s
116 0
【玉米病害识别】Python+卷积神经网络算法+人工智能+深度学习+计算机课设项目+TensorFlow+模型训练
zzy的aly
|
5月前
|
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。
zzy的aly
122 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）
子午s
|
7月前
|
机器学习/深度学习 人工智能 算法
【眼疾病识别】图像识别+深度学习技术+人工智能+卷积神经网络算法+计算机课设+Python+TensorFlow
眼疾识别系统，使用Python作为主要编程语言进行开发，基于深度学习等技术使用TensorFlow搭建ResNet50卷积神经网络算法，通过对眼疾图片4种数据集进行训练（'白内障', '糖尿病性视网膜病变', '青光眼', '正常'），最终得到一个识别精确度较高的模型。然后使用Django框架开发Web网页端可视化操作界面，实现用户上传一张眼疾图片识别其名称。
子午s
163 9
【眼疾病识别】图像识别+深度学习技术+人工智能+卷积神经网络算法+计算机课设+Python+TensorFlow

热门文章

最新文章

  • 1
    基于Python深度学习的【害虫识别】系统~卷积神经网络+TensorFlow+图像识别+人工智能
  • 2
    如何在Ubuntu上安装TensorFlow 24.04
  • 3
    通过Milvus内置Sparse-BM25算法进行全文检索并将混合检索应用于RAG系统
  • 4
    生成式 AI 大语言模型（LLMs）核心算法及源码解析：预训练篇
  • 5
    MapReduce在实现PageRank算法中的应用
  • 6
    基于生物地理算法的MLP多层感知机优化matlab仿真
  • 7
    算法系列之广度优先搜索解决妖怪和尚过河问题
  • 8
    基于PSO粒子群优化的CNN-LSTM-SAM网络时间序列回归预测算法matlab仿真
  • 9
    基于贝叶斯优化的自适应马尔科夫链蒙特卡洛(Adaptive-MCMC)算法matlab仿真
  • 10
    JavaScript 中通过Array.sort() 实现多字段排序、排序稳定性、随机排序洗牌算法、优化排序性能，JS中排序算法的使用详解（附实际应用代码）
  • 1
    基于 Python 哈希表算法的员工上网管理策略研究
    28
  • 2
    如何在Python下实现摄像头|屏幕|AI视觉算法数据的RTMP直播推送
    50
  • 3
    Apipost协议全栈支持+国密算法，调试效率飙出星际！
    32
  • 4
    Python下的毫秒级延迟RTSP|RTMP播放器技术探究和AI视觉算法对接
    66
  • 5
    大数据中的数据预处理：脏数据不清，算法徒劳！
    20
  • 6
    MapReduce在实现PageRank算法中的应用
    113
  • 7
    强化学习:时间差分(TD)(SARSA算法和Q-Learning算法)(看不懂算我输专栏)——手把手教你入门强化学习(六)
    38
  • 8
    基于 pyflink 的算法工作流设计和改造
    43
  • 9
    基于 Node.js 深度优先搜索算法的上网监管软件研究
    24
  • 10
    基于WOA鲸鱼优化的CNN-LSTM-SAM网络时间序列回归预测算法matlab仿真
    27

    • 相关课程

    更多
  • 智能运维赛（复赛）：利用数据和算法，快速定位系统异常并进行根因分析
  • 智能创作赛（复赛）：相册应用中的视频故事生成算法介绍
  • 智能创作赛（初赛）：相册应用中的故事生成算法介绍
  • 相册服务中的故事生成算法介绍
  • Go语言核心编程 - 数据结构和算法
  • 神经网络概览及算法详解

    • 相关电子书

    更多
  • 数据+算法定义新世界
  • 袋鼠云基于实时计算的反黄牛算法
  • Alink：基于Apache Flink的算法平台

    • 相关实验场景

    更多
  • 使用Swing算法实现商品推荐
  • RSA密码算法设计与实现
  • 欧拉图的构造性证明与算法实现
  • 推荐系统入门之使用ALS算法实现打分预测
    • 下一篇
    基于ECS搭建云上博客