【扒网络架构】backbone、ccff

代码猪猪傻瓜coding2024-08-10 11:49

backbone

CCFF

还不知道网络连接方式，只是知道了每一层

backbone

  1. backbone.backbone.conv1.weight torch.Size([64, 3, 7, 7])
  2. backbone.backbone.layer1.0.conv1.weight torch.Size([64, 64, 1, 1])
  3. backbone.backbone.layer1.0.conv2.weight torch.Size([64, 64, 3, 3])
  4. backbone.backbone.layer1.0.conv3.weight torch.Size([256, 64, 1, 1])
  5. backbone.backbone.layer1.0.downsample.0.weight torch.Size([256, 64, 1, 1])
  6. backbone.backbone.layer1.1.conv1.weight torch.Size([64, 256, 1, 1])
  7. backbone.backbone.layer1.1.conv2.weight torch.Size([64, 64, 3, 3])
  8. backbone.backbone.layer1.1.conv3.weight torch.Size([256, 64, 1, 1])
  9. backbone.backbone.layer1.2.conv1.weight torch.Size([64, 256, 1, 1])
  10. backbone.backbone.layer1.2.conv2.weight torch.Size([64, 64, 3, 3])
  11. backbone.backbone.layer1.2.conv3.weight torch.Size([256, 64, 1, 1])
  12. backbone.backbone.layer2.0.conv1.weight torch.Size([128, 256, 1, 1])
  13. backbone.backbone.layer2.0.conv2.weight torch.Size([128, 128, 3, 3])
  14. backbone.backbone.layer2.0.conv3.weight torch.Size([512, 128, 1, 1])
  15. backbone.backbone.layer2.0.downsample.0.weight torch.Size([512, 256, 1, 1])
  16. backbone.backbone.layer2.1.conv1.weight torch.Size([128, 512, 1, 1])
  17. backbone.backbone.layer2.1.conv2.weight torch.Size([128, 128, 3, 3])
  18. backbone.backbone.layer2.1.conv3.weight torch.Size([512, 128, 1, 1])
  19. backbone.backbone.layer2.2.conv1.weight torch.Size([128, 512, 1, 1])
  20. backbone.backbone.layer2.2.conv2.weight torch.Size([128, 128, 3, 3])
  21. backbone.backbone.layer2.2.conv3.weight torch.Size([512, 128, 1, 1])
  22. backbone.backbone.layer2.3.conv1.weight torch.Size([128, 512, 1, 1])
  23. backbone.backbone.layer2.3.conv2.weight torch.Size([128, 128, 3, 3])
  24. backbone.backbone.layer2.3.conv3.weight torch.Size([512, 128, 1, 1])
  25. backbone.backbone.layer3.0.conv1.weight torch.Size([256, 512, 1, 1])
  26. backbone.backbone.layer3.0.conv2.weight torch.Size([256, 256, 3, 3])
  27. backbone.backbone.layer3.0.conv3.weight torch.Size([1024, 256, 1, 1])
  28. backbone.backbone.layer3.0.downsample.0.weight torch.Size([1024, 512, 1, 1])
  29. backbone.backbone.layer3.1.conv1.weight torch.Size([256, 1024, 1, 1])
  30. backbone.backbone.layer3.1.conv2.weight torch.Size([256, 256, 3, 3])
  31. backbone.backbone.layer3.1.conv3.weight torch.Size([1024, 256, 1, 1])
  32. backbone.backbone.layer3.2.conv1.weight torch.Size([256, 1024, 1, 1])
  33. backbone.backbone.layer3.2.conv2.weight torch.Size([256, 256, 3, 3])
  34. backbone.backbone.layer3.2.conv3.weight torch.Size([1024, 256, 1, 1])
  35. backbone.backbone.layer3.3.conv1.weight torch.Size([256, 1024, 1, 1])
  36. backbone.backbone.layer3.3.conv2.weight torch.Size([256, 256, 3, 3])
  37. backbone.backbone.layer3.3.conv3.weight torch.Size([1024, 256, 1, 1])
  38. backbone.backbone.layer3.4.conv1.weight torch.Size([256, 1024, 1, 1])
  39. backbone.backbone.layer3.4.conv2.weight torch.Size([256, 256, 3, 3])
  40. backbone.backbone.layer3.4.conv3.weight torch.Size([1024, 256, 1, 1])
  41. backbone.backbone.layer3.5.conv1.weight torch.Size([256, 1024, 1, 1])
  42. backbone.backbone.layer3.5.conv2.weight torch.Size([256, 256, 3, 3])
  43. backbone.backbone.layer3.5.conv3.weight torch.Size([1024, 256, 1, 1])
  44. backbone.backbone.layer4.0.conv1.weight torch.Size([512, 1024, 1, 1])
  45. backbone.backbone.layer4.0.conv2.weight torch.Size([512, 512, 3, 3])
  46. backbone.backbone.layer4.0.conv3.weight torch.Size([2048, 512, 1, 1])
  47. backbone.backbone.layer4.0.downsample.0.weight torch.Size([2048, 1024, 1, 1])
  48. backbone.backbone.layer4.1.conv1.weight torch.Size([512, 2048, 1, 1])
  49. backbone.backbone.layer4.1.conv2.weight torch.Size([512, 512, 3, 3])
  50. backbone.backbone.layer4.1.conv3.weight torch.Size([2048, 512, 1, 1])
  51. backbone.backbone.layer4.2.conv1.weight torch.Size([512, 2048, 1, 1])
  52. backbone.backbone.layer4.2.conv2.weight torch.Size([512, 512, 3, 3])
  53. backbone.backbone.layer4.2.conv3.weight torch.Size([2048, 512, 1, 1])
  54. backbone.backbone.fc.weight torch.Size([1000, 2048])
  55. backbone.backbone.fc.bias torch.Size([1000])

ccf

  1. ccff.conv1.conv.weight torch.Size([3584, 3584, 1, 1])
  2. ccff.conv1.norm.weight torch.Size([3584])
  3. ccff.conv1.norm.bias torch.Size([3584])
  4. ccff.conv2.conv.weight torch.Size([3584, 3584, 1, 1])
  5. ccff.conv2.norm.weight torch.Size([3584])
  6. ccff.conv2.norm.bias torch.Size([3584])
  7. ccff.bottlenecks.0.conv1.conv.weight torch.Size([3584, 3584, 3, 3])
  8. ccff.bottlenecks.0.conv1.norm.weight torch.Size([3584])
  9. ccff.bottlenecks.0.conv1.norm.bias torch.Size([3584])
  10. ccff.bottlenecks.0.conv2.conv.weight torch.Size([3584, 3584, 1, 1])
  11. ccff.bottlenecks.0.conv2.norm.weight torch.Size([3584])
  12. ccff.bottlenecks.0.conv2.norm.bias torch.Size([3584])
  13. ccff.bottlenecks.1.conv1.conv.weight torch.Size([3584, 3584, 3, 3])
  14. ccff.bottlenecks.1.conv1.norm.weight torch.Size([3584])
  15. ccff.bottlenecks.1.conv1.norm.bias torch.Size([3584])
  16. ccff.bottlenecks.1.conv2.conv.weight torch.Size([3584, 3584, 1, 1])
  17. ccff.bottlenecks.1.conv2.norm.weight torch.Size([3584])
  18. ccff.bottlenecks.1.conv2.norm.bias torch.Size([3584])
  19. ccff.bottlenecks.2.conv1.conv.weight torch.Size([3584, 3584, 3, 3])
  20. ccff.bottlenecks.2.conv1.norm.weight torch.Size([3584])
  21. ccff.bottlenecks.2.conv1.norm.bias torch.Size([3584])
  22. ccff.bottlenecks.2.conv2.conv.weight torch.Size([3584, 3584, 1, 1])
  23. ccff.bottlenecks.2.conv2.norm.weight torch.Size([3584])
  24. ccff.bottlenecks.2.conv2.norm.bias torch.Size([3584])

input_proj

  1. input_proj.weight torch.Size([256, 3584, 1, 1])
  2. input_proj.bias torch.Size([256])

encoder

  1. encoder.layers.0.norm1.weight torch.Size([256])
  2. encoder.layers.0.norm1.bias torch.Size([256])
  3. encoder.layers.0.norm2.weight torch.Size([256])
  4. encoder.layers.0.norm2.bias torch.Size([256])
  5. encoder.layers.0.self_attn.in_proj_weight torch.Size([768, 256])
  6. encoder.layers.0.self_attn.in_proj_bias torch.Size([768])
  7. encoder.layers.0.self_attn.out_proj.weight torch.Size([256, 256])
  8. encoder.layers.0.self_attn.out_proj.bias torch.Size([256])
  9. encoder.layers.0.mlp.linear1.weight torch.Size([2048, 256])
  10. encoder.layers.0.mlp.linear1.bias torch.Size([2048])
  11. encoder.layers.0.mlp.linear2.weight torch.Size([256, 2048])
  12. encoder.layers.0.mlp.linear2.bias torch.Size([256])
  13. encoder.layers.1.norm1.weight torch.Size([256])
  14. encoder.layers.1.norm1.bias torch.Size([256])
  15. encoder.layers.1.norm2.weight torch.Size([256])
  16. encoder.layers.1.norm2.bias torch.Size([256])
  17. encoder.layers.1.self_attn.in_proj_weight torch.Size([768, 256])
  18. encoder.layers.1.self_attn.in_proj_bias torch.Size([768])
  19. encoder.layers.1.self_attn.out_proj.weight torch.Size([256, 256])
  20. encoder.layers.1.self_attn.out_proj.bias torch.Size([256])
  21. encoder.layers.1.mlp.linear1.weight torch.Size([2048, 256])
  22. encoder.layers.1.mlp.linear1.bias torch.Size([2048])
  23. encoder.layers.1.mlp.linear2.weight torch.Size([256, 2048])
  24. encoder.layers.1.mlp.linear2.bias torch.Size([256])
  25. encoder.layers.2.norm1.weight torch.Size([256])
  26. encoder.layers.2.norm1.bias torch.Size([256])
  27. encoder.layers.2.norm2.weight torch.Size([256])
  28. encoder.layers.2.norm2.bias torch.Size([256])
  29. encoder.layers.2.self_attn.in_proj_weight torch.Size([768, 256])
  30. encoder.layers.2.self_attn.in_proj_bias torch.Size([768])
  31. encoder.layers.2.self_attn.out_proj.weight torch.Size([256, 256])
  32. encoder.layers.2.self_attn.out_proj.bias torch.Size([256])
  33. encoder.layers.2.mlp.linear1.weight torch.Size([2048, 256])
  34. encoder.layers.2.mlp.linear1.bias torch.Size([2048])
  35. encoder.layers.2.mlp.linear2.weight torch.Size([256, 2048])
  36. encoder.layers.2.mlp.linear2.bias torch.Size([256])
  37. encoder.norm.weight torch.Size([256])
  38. encoder.norm.bias torch.Size([256])

ope

  1. ope.iterative_adaptation.layers.0.norm1.weight torch.Size([256])
  2. ope.iterative_adaptation.layers.0.norm1.bias torch.Size([256])
  3. ope.iterative_adaptation.layers.0.norm2.weight torch.Size([256])
  4. ope.iterative_adaptation.layers.0.norm2.bias torch.Size([256])
  5. ope.iterative_adaptation.layers.0.norm3.weight torch.Size([256])
  6. ope.iterative_adaptation.layers.0.norm3.bias torch.Size([256])
  7. ope.iterative_adaptation.layers.0.self_attn.in_proj_weight torch.Size([768, 256])
  8. ope.iterative_adaptation.layers.0.self_attn.in_proj_bias torch.Size([768])
  9. ope.iterative_adaptation.layers.0.self_attn.out_proj.weight torch.Size([256, 256])
  10. ope.iterative_adaptation.layers.0.self_attn.out_proj.bias torch.Size([256])
  11. ope.iterative_adaptation.layers.0.enc_dec_attn.in_proj_weight torch.Size([768, 256])
  12. ope.iterative_adaptation.layers.0.enc_dec_attn.in_proj_bias torch.Size([768])
  13. ope.iterative_adaptation.layers.0.enc_dec_attn.out_proj.weight torch.Size([256, 256])
  14. ope.iterative_adaptation.layers.0.enc_dec_attn.out_proj.bias torch.Size([256])
  15. ope.iterative_adaptation.layers.0.mlp.linear1.weight torch.Size([2048, 256])
  16. ope.iterative_adaptation.layers.0.mlp.linear1.bias torch.Size([2048])
  17. ope.iterative_adaptation.layers.0.mlp.linear2.weight torch.Size([256, 2048])
  18. ope.iterative_adaptation.layers.0.mlp.linear2.bias torch.Size([256])
  19. ope.iterative_adaptation.layers.1.norm1.weight torch.Size([256])
  20. ope.iterative_adaptation.layers.1.norm1.bias torch.Size([256])
  21. ope.iterative_adaptation.layers.1.norm2.weight torch.Size([256])
  22. ope.iterative_adaptation.layers.1.norm2.bias torch.Size([256])
  23. ope.iterative_adaptation.layers.1.norm3.weight torch.Size([256])
  24. ope.iterative_adaptation.layers.1.norm3.bias torch.Size([256])
  25. ope.iterative_adaptation.layers.1.self_attn.in_proj_weight torch.Size([768, 256])
  26. ope.iterative_adaptation.layers.1.self_attn.in_proj_bias torch.Size([768])
  27. ope.iterative_adaptation.layers.1.self_attn.out_proj.weight torch.Size([256, 256])
  28. ope.iterative_adaptation.layers.1.self_attn.out_proj.bias torch.Size([256])
  29. ope.iterative_adaptation.layers.1.enc_dec_attn.in_proj_weight torch.Size([768, 256])
  30. ope.iterative_adaptation.layers.1.enc_dec_attn.in_proj_bias torch.Size([768])
  31. ope.iterative_adaptation.layers.1.enc_dec_attn.out_proj.weight torch.Size([256, 256])
  32. ope.iterative_adaptation.layers.1.enc_dec_attn.out_proj.bias torch.Size([256])
  33. ope.iterative_adaptation.layers.1.mlp.linear1.weight torch.Size([2048, 256])
  34. ope.iterative_adaptation.layers.1.mlp.linear1.bias torch.Size([2048])
  35. ope.iterative_adaptation.layers.1.mlp.linear2.weight torch.Size([256, 2048])
  36. ope.iterative_adaptation.layers.1.mlp.linear2.bias torch.Size([256])
  37. ope.iterative_adaptation.layers.2.norm1.weight torch.Size([256])
  38. ope.iterative_adaptation.layers.2.norm1.bias torch.Size([256])
  39. ope.iterative_adaptation.layers.2.norm2.weight torch.Size([256])
  40. ope.iterative_adaptation.layers.2.norm2.bias torch.Size([256])
  41. ope.iterative_adaptation.layers.2.norm3.weight torch.Size([256])
  42. ope.iterative_adaptation.layers.2.norm3.bias torch.Size([256])
  43. ope.iterative_adaptation.layers.2.self_attn.in_proj_weight torch.Size([768, 256])
  44. ope.iterative_adaptation.layers.2.self_attn.in_proj_bias torch.Size([768])
  45. ope.iterative_adaptation.layers.2.self_attn.out_proj.weight torch.Size([256, 256])
  46. ope.iterative_adaptation.layers.2.self_attn.out_proj.bias torch.Size([256])
  47. ope.iterative_adaptation.layers.2.enc_dec_attn.in_proj_weight torch.Size([768, 256])
  48. ope.iterative_adaptation.layers.2.enc_dec_attn.in_proj_bias torch.Size([768])
  49. ope.iterative_adaptation.layers.2.enc_dec_attn.out_proj.weight torch.Size([256, 256])
  50. ope.iterative_adaptation.layers.2.enc_dec_attn.out_proj.bias torch.Size([256])
  51. ope.iterative_adaptation.layers.2.mlp.linear1.weight torch.Size([2048, 256])
  52. ope.iterative_adaptation.layers.2.mlp.linear1.bias torch.Size([2048])
  53. ope.iterative_adaptation.layers.2.mlp.linear2.weight torch.Size([256, 2048])
  54. ope.iterative_adaptation.layers.2.mlp.linear2.bias torch.Size([256])
  55. ope.iterative_adaptation.norm.weight torch.Size([256])
  56. ope.iterative_adaptation.norm.bias torch.Size([256])

ope.shape_or_objectness

  1. ope.shape_or_objectness.0.weight torch.Size([64, 2])
  2. ope.shape_or_objectness.0.bias torch.Size([64])
  3. ope.shape_or_objectness.2.weight torch.Size([256, 64])
  4. ope.shape_or_objectness.2.bias torch.Size([256])
  5. ope.shape_or_objectness.4.weight torch.Size([2304, 256])
  6. ope.shape_or_objectness.4.bias torch.Size([2304])

回归头

  1. regression_head.regressor.0.layer.0.weight torch.Size([128, 256, 3, 3])
  2. regression_head.regressor.0.layer.0.bias torch.Size([128])
  3. regression_head.regressor.1.layer.0.weight torch.Size([64, 128, 3, 3])
  4. regression_head.regressor.1.layer.0.bias torch.Size([64])
  5. regression_head.regressor.2.layer.0.weight torch.Size([32, 64, 3, 3])
  6. regression_head.regressor.2.layer.0.bias torch.Size([32])
  7. regression_head.regressor.3.weight torch.Size([1, 32, 1, 1])
  8. regression_head.regressor.3.bias torch.Size([1])

辅助头

  1. aux_heads.0.regressor.0.layer.0.weight torch.Size([128, 256, 3, 3])
  2. aux_heads.0.regressor.0.layer.0.bias torch.Size([128])
  3. aux_heads.0.regressor.1.layer.0.weight torch.Size([64, 128, 3, 3])
  4. aux_heads.0.regressor.1.layer.0.bias torch.Size([64])
  5. aux_heads.0.regressor.2.layer.0.weight torch.Size([32, 64, 3, 3])
  6. aux_heads.0.regressor.2.layer.0.bias torch.Size([32])
  7. aux_heads.0.regressor.3.weight torch.Size([1, 32, 1, 1])
  8. aux_heads.0.regressor.3.bias torch.Size([1])
  9. aux_heads.1.regressor.0.layer.0.weight torch.Size([128, 256, 3, 3])
  10. aux_heads.1.regressor.0.layer.0.bias torch.Size([128])
  11. aux_heads.1.regressor.1.layer.0.weight torch.Size([64, 128, 3, 3])
  12. aux_heads.1.regressor.1.layer.0.bias torch.Size([64])
  13. aux_heads.1.regressor.2.layer.0.weight torch.Size([32, 64, 3, 3])
  14. aux_heads.1.regressor.2.layer.0.bias torch.Size([32])
  15. aux_heads.1.regressor.3.weight torch.Size([1, 32, 1, 1])
  16. aux_heads.1.regressor.3.bias torch.Size([1])

Total number of parameters in LOCA: 447974251

Total number of parameters in CCFF: 411099136（这个模块，参数量好大）

相关推荐
维度攻城狮9 分钟前
高效创建工作流，可实现类似unreal engine的蓝图效果，内部使用多线程高效执行节点函数
python·游戏引擎·开源软件·虚幻·graph·工作流
MiyamiKK5711 分钟前
leetcode_数组 189. 轮转数组
python·算法·leetcode·职场和发展
cheryl881 小时前
Python+Requests 企业级接口测试入门（1~3天）
开发语言·python
Linhieng1 小时前
Pyinstaller 打包程序后出现：ValueError: Invalid async_mode specified，开发环境没问题
python
爱的叹息2 小时前
Spring MVC 操作会话属性详解（@SessionAttributes 与 @SessionAttribute）
python·spring·mvc
大刘讲IT2 小时前
构建实时、融合的湖仓一体数据分析平台：基于 Delta Lake 与 Apache Iceberg
开发语言·python·sql·mysql·数据挖掘·数据分析·json
databook2 小时前
决策树剪枝：平衡模型复杂性与泛化能力
python·机器学习·scikit-learn
编程想法2 小时前
某网站防爬虫/防盗资源的实现和破防
后端·爬虫·python
江节胜-胜行全栈AI2 小时前
Java-对比两组对象找出发生变化的字段工具-支持枚举映射-支持时间-支持显示对应字段中文描述-嵌套list等场景
java·python·list
T - mars3 小时前
python爬虫：喜马拉雅登录案例
开发语言·python
热门推荐
01RAG 实践- Ollama+RagFlow 部署本地知识库02我决定放弃搞 Java 了03如何在WPS和Word/Excel中直接使用DeepSeek功能04空中无人机等动态目标识别2025.4.405汽车上的各种质量：整备质量、总质量、装载质量、簧上质量、簧下质量06DeepSeek各版本说明与优缺点分析07如何用deepseek生成流程图08生活电子常识--删除谷歌浏览器搜索记录09从零安装 LLaMA-Factory 微调 Qwen 大模型成功及所有的坑10DeepSeek RAGFlow构建本地知识库系统