Models icon indicating copy to clipboard operation
Models copied to clipboard

采用MegEngine实现的各种主流深度学习模型

Results 17 Models issues
Sort by recently updated
recently updated
newest added

## 任务描述 - 复现 EfficientNet ,训练正常收敛,验收指标符合预期,并将代码提交到 offical/vision/classification/models 下 ## 目标 - 数据集ImageNet - 准确率和论文一致或更高 - 脚本可以完整完成训练步骤 - 提供训练后的权重文件 - 提交至 https://github.com/MegEngine/Hub

help-wanted

## 任务描述 - 复现 InceptionNet ,训练正常收敛,验收指标符合预期,并将代码提交到 offical/vision/classification/models 下 ## 目标 - 数据集ImageNet - 准确率和论文一致或更高 - 脚本可以完整完成训练步骤 - 提供训练后的权重文件 - 提交至 https://github.com/MegEngine/Hub

help-wanted

参考实现:[DALLE-pytorch](https://github.com/lucidrains/DALLE-pytorch) [DALL-E](https://github.com/openai/DALL-E) - [x] OpenaiDicreteVAE编写 - [x] OpenaiDicreteVAE与训练权重转换 - [x] OpenaiDicreteVAE对齐 - [x] Attention编写 - [x] Attention对齐 - [x] SparseConvolutionAttention编写 - [x] SparseConvolutionAttention对齐 - [x] SparseAxialAttention编写 - [x] SparseAxialAttention对齐 -...

参考实现:[taming-transformers](https://github.com/CompVis/taming-transformers) - [x] diffusion modules、Encoder、Decoder编写 - [x] diffusion modules、Encoder、Decoder对齐 - [x] diffusion modules、Encoder、Decoder权重转换脚本 - [x] VectorQuantizer编写 - [x] VectorQuantizer对齐 - [x] gumbel_softmax编写 - [x] gumbel_softmax对齐 - [x] GumbelQuantize编写 - [x]...

参考实现 [big-sleep](https://github.com/lucidrains/big-sleep) - [x] spectral_norm编写 - [x] spectral_norm对齐 - [x] BigGAN预训练权重转换 - [x] BigGAN前向对齐 - [x] EMA及resample等工具函数编写 - [x] EMA及resample等工具函数对齐 - [x] Latents编写 - [x] Latents对齐 - [x] BigSleep编写 -...

## 环境 1.系统环境:Ubuntu 22.04.2 2.MegEngine版本:1.13.0 3.python版本:3.10.12 4.模型名称:atss_res18_coco_3x_800size ## 复现步骤 1.训练 ``` python official/vision/detection/tools/train.py -f official/vision/detection/configs/atss_res18_coco_3x_800size.py -n 1 -d data/coco/ ``` 2.convert ``` python convert.py -f official/vision/detection/configs/atss_res18_coco_3x_800size.py -w log-of-atss_res18_coco_3x_800size/epoch_9.pkl -i official/assets/cat.jpg...

## 背景 本人在测试训练语义分割模型时,因为数据格式不同,采用自己编写的数据集生成器进行训练。 ## 任务描述 训练时偶发性报错。 terminate called after throwing an instance of 'mgb::CudaError' what(): failed to query event: 700: an illegal memory access was encountered backtrace: /opt/conda/lib/python3.6/site-packages/megengine/core/lib/libmegengine_shared.so(_ZN3mgb9CudaErrorC1ERKSs+0x54) [0x7f30e95ae164] /opt/conda/lib/python3.6/site-packages/megengine/core/lib/libmegengine_shared.so(_ZN3mgb12CudaCompNode9EventImpl11do_finishedEv+0xbc)...