Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
|
1 year ago | |
---|---|---|
.. | ||
__init__.py | 1 year ago | |
bpe_simple_vocab_16e6.txt.gz | 1 year ago | |
clip.py | 1 year ago | |
mha.py | 1 year ago | |
model.py | 1 year ago | |
simple_tokenizer.py | 1 year ago |
冻结ViT-B/32版本的CLIP模型中的全部图像层,用Adan优化器训练模型,训练100个epoch,每隔5个epoch对模型进行保存;完成CLIP模型训练后,运行test_clip.py用测试集中的数据和自定义的提示词对保存的模型进行测试,选取测试精度最好的模型和对应的提示词,运行predict.py文件,选择“min_loss.pth”模型,提交官方系统测试,top1的精度是0.6788。
Python Text Markdown