EADST

Pytorch: Freeze layers to Finetune the Model

作者：XD / 发表： 2023年2月23日 22:02 / 更新： 2023年2月23日 22:03 / 编程笔记 / 阅读量：969

Pytorch: Freeze layers to Finetune the Model.

for k, v in model.named_parameters():
    print(k) # check the layer name
for k, v in model.named_parameters():
    if k in ["last.weight", "last.bias"]: # freeze the layer with the given name list
        v.requires_grad = True
    else:
        v.requires_grad = False

本文作者：XD 转载请标明出处：http://www.eadst.com/blog/166

本站采用知识共享署名-非商业性使用-相同方式共享 4.0 国际许可协议进行许可。

上一篇
Numpy: Obtain the Indices to Sort An Array
下一篇
Python: Get the Mode of One List
相关标签
Pytorch
About Me
XD
Goals determine what you are going to be.
Category
标签云
Github LLM Bitcoin Input Interview Nginx 阿里云 Heatmap Crawler Linux OpenCV Plotly git LoRA Knowledge ONNX Safetensors Land Pillow FlashAttention Bert AI Ubuntu Math Web uWSGI PIP Image2Text Google GIT Attention Password Baidu MD5 Qwen2.5 torchinfo Diagram Docker Hilton SQL 关于博主 Hungarian GPTQ SPIE BeautifulSoup Paddle GoogLeNet Food Python Tensor scipy llama.cpp NameSilo C++ Pytorch Distillation Paper Card ResNet-50 VGG-16 Markdown Hotel EXCEL Data 算法题 v2ray NLP NLTK Numpy Color 域名 FastAPI QWEN Zip Ptyhon Magnet HaggingFace Dataset COCO 签证 Anaconda Tracking LLAMA VPN Michelin Clash GGML Bipartite PDF 搞笑 CEIR Permission CUDA ModelScope SVR FP64 transformers uwsgi GPT4 Shortcut DeepStream Video 报税 hf Windows BF16 FP32 LeetCode diffusers FP16 OCR Datetime Plate Disk YOLO LaTeX Domain Excel Template UNIX CAM ChatGPT Proxy Sklearn Algorithm CV logger Quantize tar Conda PyCharm Bin Qwen Streamlit Review CTC Use TensorRT Transformers Vmess Pickle HuggingFace OpenAI Jetson VSCode Tiktoken WebCrawler RGB git-lfs Gemma SQLite BTC Augmentation InvalidArgumentError Website Pandas Quantization Git XGBoost TensorFlow Translation CSV 腾讯云 XML Cloudreve JSON Random Django TSV Statistics Vim Base64
站点统计

本站现有博文266篇,共被浏览440677次

本站已经建立2019天!

热门文章
文章归档
回到顶部