训练报告: 01181504_e50_w90_fast

训练环境与参数(train)
变量名 含义
time_start 开始时间 2026-01-18 13:54:10
platform 平台 Linux-5.10.134-18.0.6.lifsea8.x86_64-x86_64-with-glibc2.35
processor CPU架构 x86_64
python_version Python版本 3.10.6
torch_version Torch版本 2.0.0+cu118
cuda_available CUDA可用 False
cuda_device_count GPU数量 0
cuda_device_name_0 GPU0名称 NA
device_used 使用设备 cpu
epochs 训练轮数 50
train_seconds 训练时长 1小时9分钟48秒
threshold_default 默认阈值 0.5
pos_weight_used pos_weight 90.0
lr_init 初始学习率 1e-3
optimizer 优化器 Adam
report_folder_name 报告名 01181504_e50_w90
测试环境与参数(cut_test)
变量名 含义
time 记录时间 2026-01-18 15:05:48
platform 平台 Linux-5.10.134-18.0.6.lifsea8.x86_64-x86_64-with-glibc2.35
processor CPU架构 x86_64
python_version Python版本 3.10.6
torch_version Torch版本 2.0.0+cu118
cuda_available CUDA可用 False
device_used 使用设备 cpu
threshold_default 默认阈值 0.5
batch_size batch_size 64
report_folder_name 报告名 01181504_e50_w90
训练集曲线(epoch_metrics)
Loss
Precision / Recall / F1
AP(PR-AUC) / AUC(ROC)
Accuracy(若无则为空)
正类预测率 pos_pred_rate
学习率 lr(若无则为空)
建议阅读顺序:先看 pos_pred_rate 判断“乱报切点”程度,再看 PRF 是否平衡,最后结合 AP/AUC 评估整体质量。
训练集最终指标(train / val 汇总)
阈值 0.5
精确率 0.09042553191489362
召回率 0.9444444444444444
F1 0.1650485436893204
准确率 0.8097345132743363
AP(PR-AUC) 0.7061769172667288
AUC(ROC) 0.9758276899924756
TP 17
FP 171
TN 715
FN 1
正类预测率 0.2079646017699115
测试集最终指标(cut_test)
阈值 0.5
精确率 0.1164383561643836
召回率 0.85
F1 0.2048192771084337
准确率 0.9025830258302583
AP(PR-AUC) 0.7414643967686846
AUC(ROC) 0.9658801498127341
TP 17
FP 129
TN 1206
FN 3
正类预测率 0.1077490774907749
测试集帧轴可视化(每个视频:TP / FP / FN 的帧位置)
TP(预测=切点 且 GT=切点) FP(预测=切点 但 GT=非切点) FN(GT=切点 但 预测=非切点) 提示:鼠标悬停点可看帧号
V001.mp4
total_frames: 43  |  TP 1 FP 1 FN 0
GT cuts: 1 Pred cuts: 2
轴左侧≈frame 0 轴右侧≈frame 42
V002.mp4
total_frames: 161  |  TP 1 FP 8 FN 1
GT cuts: 2 Pred cuts: 9
轴左侧≈frame 0 轴右侧≈frame 160
V003.mp4
total_frames: 122  |  TP 5 FP 18 FN 0
GT cuts: 5 Pred cuts: 23
轴左侧≈frame 0 轴右侧≈frame 121
V004.mp4
total_frames: 700  |  TP 4 FP 0 FN 2
GT cuts: 6 Pred cuts: 4
轴左侧≈frame 0 轴右侧≈frame 699
V005.mp4
total_frames: 334  |  TP 6 FP 102 FN 0
GT cuts: 6 Pred cuts: 108
轴左侧≈frame 0 轴右侧≈frame 333
测试集数据明细(Excel 其它 Sheets 预览)
dataset_summary(显示前 11 行 / 共 11 行)
item value
num_videos 5
num_pairs 1355
num_cuts 20
num_non_cuts 1335
pos_ratio 0.01476014760147601
per_video_frame_stats
min_frames 43
max_frames 700
mean_frames 272
median_frames 161
per_video(显示前 5 行 / 共 5 行)
vid vid_idx total_frames gt_cut_count pred_cut_count tp fp fn gt_cuts pred_cuts
V001.mp4 0 43 1 2 1 1 0 26 20,26
V002.mp4 1 161 2 9 1 8 1 86,131 86,96,140,154,155,156,157,158,159
V003.mp4 2 122 5 23 5 18 0 18,35,56,72,105 18,21,25,29,35,40,42,43,44,47,48,49,51,52,53,55,56,61,63,72,92,95,105
V004.mp4 3 700 6 4 4 0 2 46,419,457,504,600,643 46,419,504,643
V005.mp4 4 334 6 108 6 102 0 20,69,134,169,238,263 10,11,12,13,14,15,16,17,18,19,20,21,29,30,31,32,33,35,36,44,45,46,48,49,50,54,55,57,58,59,60,61,62,63,64,65,69,70,78,79,80,81,84,97,98,99,100,101,103,110,113,114,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,169,171,173,174,176,178,183,184,186,198,199,201,213,219,221,223,226,238,263,265,267,269,272,274,276,277,280,281,282,284,285,286,287,311,312,314,324,325,329,330,331
classification_report(显示前 5 行 / 共 5 行)
text
precision recall f1-score support
Non-cut 0.9975 0.9034 0.9481 1335
Cut 0.1164 0.8500 0.2048 20
accuracy 0.9026 1355
下载