LiLiLiam

Results 7 issues of LiLiLiam

`model_dir = './pd_model'` `quant_post_static(executor=exe, model_dir=model_dir, model_filename=model_filename, params_filename=params_filename, quantize_model_path=save_model_path, sample_generator=sample_generator, batch_size=batch_size, batch_nums=batch_nums, algo=algo, quantizable_op_type=quantizable_op_type) ` 如上,作静态量化时,model_dir下应该放什么文件,我目前放的是x2paddle生成的model.pdiparams文件、model.pdmodel文件和model.pdiparams.info,运行时报错`[Errno 2] No such file or directory: 'pd_model/__model__'`

请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem - 系统环境/System Environment:windows - 版本号/Version:Paddle:2.6 PaddleOCR: 问题相关组件/Related components: - 运行指令/Command Code:python3 tools/train.py -c configs/det/det_r50_vd_dcn_fce_ctw.yml - 完整报错/Complete Error Message: Traceback (most...

`src = wrapbuffer_virtualaddr((void *)img.data, img_width, img_height, RK_FORMAT_RGB_888); dst = wrapbuffer_virtualaddr((void *)resize_buf, width, height, RK_FORMAT_RGB_888);` demo里的默认的输入图像时三通道的,我现在需要输入灰度图应该怎么改?

![image](https://user-images.githubusercontent.com/65694997/189903753-f58b0c8b-2cc6-40b1-8f2c-db6f1ca5c7f8.png) ![image](https://user-images.githubusercontent.com/65694997/189903624-23d51816-cc53-45e4-bcc8-f6b2e9f8b31b.png) 在使用demo中你们自定义imresize对输入图像进行resize后,图片会整体向右移动,应该是imresize函数里的坐标有问题

我需要在一个question中对多张图进行联合推理,以下是我的部分代码: content_images = [] for idx in range(len(image_files)): # content.append({"type": "image", "image": image_files[idx]}) content_images.append("data:image,{}".format(image_to_base64(image_files[idx], max_size=1024))) conversation = [ { "role": "", "content": f"\n{query}", "images": content_images, }, {"role": "", "content": ""},...