-
-
1-0_课程介绍[防断更微mmj4408].mp4
-
10-1.2.3_梯度问题与ResNet[防断更微mmj4408].mp4
-
11-1.3.1_ResNet垃圾分类任务介绍[防断更微mmj4408].mp4
-
12-1.3.2_ResNet垃圾分类数据集预处理[防断更微mmj4408].mp4
-
13-1.3.3_ResNet垃圾分类数据读取[防断更微mmj4408].mp4
-
14-1.3.4_ResNet垃圾分类模型训练[防断更微mmj4408].vep
-
15-1.3.5_ResNet垃圾分类模型测试[防断更微mmj4408].vep
-
16-1.3.6_ResNet垃圾分类模型调优[防断更微mmj4408].vep
-
17-2.1.0_经典模型的宽度设计思想_简介[防断更微mmj4408].vep
-
18-2.1.1_通道数量调整[防断更微mmj4408].vep
-
19-2.1.2_多分支网络结构[防断更微mmj4408].vep
-
2-1.1.0_经典浅层卷积网络设计_简介[防断更微mmj4408].mp4
-
20-2.1.3_通道补偿技术[防断更微mmj4408].vep
-
21-2.2.0_网络宽度对模型性能影响_简介[防断更微mmj4408].vep
-
22-2.2.1_多通道的网络Inception-v1[防断更微mmj4408].vep
-
23-2.2.2_拓宽的残差网络ResNeXt[防断更微mmj4408].vep
-
24-2.3.1_InceptionNet花卉分类实战-项目简介[防断更微mmj4408].vep
-
25-2.3.2_InceptionNet花卉分类实战-模型搭建（In[防断更微mmj4408].vep
-
26-2.3.3_InceptionNet花卉分类实战-模型搭建（In[防断更微mmj4408].vep
-
27-2.3.4_InceptionNet花卉分类实战-模型搭建（In[防断更微mmj4408].vep
-
28-2.3.5_InceptionNet花卉分类实战-模型训练[防断更微mmj4408].vep
-
29-2.3.6_InceptionNet花卉分类实战-模型测试[防断更微mmj4408].vep
-
3-1.1.1_Neocognitron[防断更微mmj4408].mp4
-
31-3.1.1_STN[防断更微mmj4408].vep
-
32-3.1.2_DynamicCapacityNetworks[防断更微mmj4408].vep
-
33-3.1.3_Learn to Pay Attention[防断更微mmj4408].vep
-
34-3.2.1_SENet[防断更微mmj4408].vep
-
35-3.2.2_SKNet[防断更微mmj4408].vep
-
36-3.2.3_ResNeSt[防断更微mmj4408].vep
-
37-3.3.1_CBAM[防断更微mmj4408].vep
-
38-3.3.2_BAM[防断更微mmj4408].vep
-
39-3.3.3_ResidualAttention[防断更微mmj4408].vep
-
4-1.1.2_TDNN[防断更微mmj4408].mp4
-
40-3.3.4_Dual Attention Network[防断更微mmj4408].vep
-
41-3.4.1_基于SENet模型的人种分类-数据集介绍与读取[防断更微mmj4408].vep
-
42-3.4.2_基于SENet模型的人种分类-模型搭建通用模板[防断更微mmj4408].vep
-
43-3.4.3_基于SENet模型的人种分类-从零搭建ResNet模[防断更微mmj4408].vep
-
44-3.4.4_基于SENet模型的人种分类-模型训练通用模板[防断更微mmj4408].vep
-
45-3.4.5_基于SENet模型的人种分类-SENet模型搭建与训[防断更微mmj4408].vep
-
47-4.1.1_Xception理论介绍[防断更微mmj4408].vep
-
48-4.1.2_Xception代码讲解[防断更微mmj4408].vep
-
49-4.2.1_MobileNet V1理论介绍[防断更微mmj4408].vep
-
5-1.1.3_Cresceptron[防断更微mmj4408].mp4
-
50-4.2.2_MobileNet V1代码讲解[防断更微mmj4408].vep
-
51-4.3.1_MobileNet V2理论介绍[防断更微mmj4408].vep
-
52-4.3.2_MobileNet V2代码讲解[防断更微mmj4408].vep
-
53-4.4.1_shufflenetv1_理论[防断更微mmj4408].vep
-
54-4.4.2_shufflenetv1_代码[防断更微mmj4408].vep
-
55-4.5.1_shufflenetv2理论[防断更微mmj4408].vep
-
56-4.5.2_shufflenetv2代码[防断更微mmj4408].vep
-
57-4.6.1_squeezenet理论[防断更微mmj4408].vep
-
58-4.6.2_squeezenet代码[防断更微mmj4408].vep
-
6-1.1.4_LeNet[防断更微mmj4408].mp4
-
60-5.1.1_通用的分类任务训练代码[防断更微mmj4408].vep
-
61-5.1.2_利用Tensorboard监控训练速度[防断更微mmj4408].vep
-
62-5.1.3_通用的分类任务预测代码[防断更微mmj4408].vep
-
63-5.2.1_Pytorch模型格式转换与优化[防断更微mmj4408].vep
-
64-5.2.2_安卓部署单张图片识别app[防断更微mmj4408].vep
-
65-5.2.3_安卓部署实时识别app[防断更微mmj4408].vep
-
7-1.2.0_网络深度对分类模型的影响_简介[防断更微mmj4408].mp4
-
8-1.2.1_经典的网络AlexNet[防断更微mmj4408].mp4
-
9-1.2.2_更深的网络VGGNet[防断更微mmj4408].mp4
-