liyuyuan6969

AssertionError: feed_list should be set when return_list=False

7

# 场景描述 我正在量化paddle里面的关键点检测模型，我参考的[量化文档](https://paddleslim.readthedocs.io/zh_CN/latest/api_cn/static/quant/quantization_api.html#quant-post-dynamic)，但是我还是不是很懂sample_generator这个参数要怎么传？然后我看代码里面的加载数据集的方式是先调用`self.dataset = cfg['{}Dataset'.format(self.mode.capitalize())]`来构造一个对象，然后使用`self.loader = create('{}Reader'.format(self.mode.capitalize()))( self.dataset, cfg.worker_num)`来构造一个loader， 最后推理的方式为 ``` for step_id, data in enumerate(self.loader): self.status['data_time'].update(time.time() - iter_tic) self.status['step_id'] = step_id profiler.add_profiler_step(profiler_options) self._compose_callback.on_step_begin(self.status) data['epoch_id'] = epoch_id if self.cfg.get('amp', False):...

在论坛上也问了下！ 问题链接：https://aistudio.baidu.com/paddle/forum/topic/show/994140 这个项目的ISSURE怎么像在都没人回了？论坛也没人回，xdm有其他的量化工具推荐吗？

hello,i use deepspeed-chat training model,now,i start train step3,RLHF training,But i do not know how many epoch and my model parameters will be ok.One hours or longer?Can you give me some...

``` // DCNv2.cu int kernel_size = weights_shape.d[W_DIM]; size_t maskSize = static_cast(input1_shape.d[H_DIM] * input1_shape.d[W_DIM] * kernel_size * kernel_size * deformable_groups); size_t im2colSize = static_cast(input1_shape.d[C_DIM] * kernel_size * kernel_size * output_shape.d[H_DIM] *...