nkjulia

安装失败问题

1

错误片段，麻烦告知下，如何处理呢？ /code/pyltp/pyltp/ltp/thirdparty/eigen/Eigen/src/Core/arch/AVX512/PacketMath.h: In function ‘Packet Eigen::internal::preduxp(const Packet*) [with Packet = __vector(16) float]’: /code/pyltp/pyltp/ltp/thirdparty/eigen/Eigen/src/Core/arch/AVX512/PacketMath.h:663:56: error: expected ‘,’ or ‘;’ before ‘__m256’ __m256 OUTPUT##_0 = _mm512_extractf32x8_ps(INPUT, 0) __m256 OUTPUT##_1 = \ ^~~~~~...

fix errors when using eval mode

1

fix errors when evaluate using script onsets_frames_transcription_train.py related issue #1919

Questions about onset and frames pretrained model (maestro_checkpoint.zip)

1

i clone the latest code and download the pretrained model ( maestro_checkpoint.zip) to train my own model and did not change any model parameters. i inspect the pretrained checkpoint and...

根据网上的建议，已经把每个图片转成了RGB格式，然后再生成tfrecord，依然报错，有遇到的同学吗 

finetune alpaca-lora with custom dataset got poor results

19

i have finetuned alpaca-lora with about 60 thousand records just for generating prompts for text to image tasks like stable diffusion. the decrease in loss is in line with expectations,...

all result is 0

10

i try to use the example script to assess some images.but i got 0 for all the images.why? ``` import pyiqa import torch # list all available metrics print(pyiqa.list_models()) device...

i replace the llm by gpt2 and finetune it on cc_sbu_align got Nan Loss

4

hi ,i met such promblem. i replace the llm part by gpt2, and change the project layer, froze vit and qformer , finetune the project layer and gpt2 ,but got...