-
from keras.models import load_model
model = load_model('m32.h5')
model.summary()
Running the above code in google colab and getting following error.
OSError: Unable to open file (file signatur…
-
To the Authors
Very nice job! But I just have some questions when I read the paper:
1) you concatenate all category names as input texts for object detection tasks, but how to deal with the texts …
-
**Description:**
As we aim to make `burn-wgpu` more versatile in terms of browser compatibility, there's a need to enhance its ability to fall back to WebGL when WebGPU is unsupported.
**Details:*…
-
I have seen multiple references in PaddlePaddle code to transpiling to float16 with gains on Volta GPUs. This out of date doc gives instructions but I can't find anything for recent versions:
http://…
-
how to use wholegraph in branch-23.10,I cannot find the guide of it
-
**Is your feature request related to a problem? Please describe.**
I'm always frustrated when the path pf my file was always start with /data/upload/1 , and it is not my real file path , I found alth…
-
Hi， The heatmap in this paper is used for classification and positioning at the same time. Your network only uses the classification information of heatmap, right？
-
I've selected for refactoring 12 lines of code which are duplicated in 2 file(s) ([1](https://github.com/Shinkai125/Band/blob/8a7aa23593941d9f443288b8bd56bc47f006ee83/example/transformer_distill_to_bi…
-
### bug描述 Describe the Bug
paddle 版本：paddlepaddle/paddle:2.4.0-gpu-cuda11.2-cudnn8.1-trt8.0
模型训练脚本：
train_path = 'python3.7 paddle_classfication.py'
使用subprocess 脚本 启动模型训练脚本：
proc = subprocess.…
-
没有看到有分类代码，自己写了一个。
简单的做了数据均衡和数据增强，然后finetune了bert-chinese，划分出来的测试集上acc 93%。
目前看标签确实有一些问题，比如“股票”和“财经”标签下的数据是混杂的，最好能有对于数据标签准确率等方面的评估指标。