hxuaj
hxuaj
Same problem occurred. The performance becomes worse as the words grow up, including Chinese characters and formula. Specifically, the response speed turns out slow(1-2 seconds lagging) when typing Chinese Characters...
查了一下ppyoloe_crn_l_300e_coco的默认配置，在ppyoloe_crn.yml中找到了关于PPYOLOEHead的配置如下： ```yaml PPYOLOEHead: fpn_strides: [32, 16, 8] grid_cell_scale: 5.0 grid_cell_offset: 0.5 static_assigner_epoch: 100 use_varifocal_loss: True loss_weight: {class: 1.0, iou: 2.5, dfl: 0.5} static_assigner: name: ATSSAssigner topk: 9 assigner: name: TaskAlignedAssigner...
> Hey @hxuaj, sorry for the troubles. > > The first error should be fixed by setting the `CUDA_VISIBLE_DEVICES` env variable to one of your devices (0 or 1), either...
> It first appears in  Just submitted a issue related to notations in this chapter before noticing yours. https://github.com/christophM/interpretable-ml-book/issues/331#issue-1266040460 I suppose $X_C$ is the current instance of interest, and...
> Hi at first I want to say that is the best Faster RCNN I could find which is created with Tensorflow2. > > I try this one and change...
Please specify: * how many images are there in your own dataset? * how many epochs have you trained? If the dataset is small or not enough epochs, chances are...
During sanity check, you can monitor the gradient flow(input->loss->grads->weights) to see if the model was actually got trained, which is a proper way to locate the bug in code.
谢谢回复，希望以后能有相关的功能。
在4张T4卡上跑成功了。改了两个地方： 首先是原cli_demo_multi_gpus.py中device_map改成如下： ```python device_map = infer_auto_device_map( model=model, max_memory={i: max_memory_per_gpu for i in range(num_gpus)}, no_split_module_classes=["CogVLMDecoderLayer", "TransformerLayer", "Block"] ) ``` 然后是在模型的module中的visual.py里的EVA2CLIPModel的forward中将boi和eoi传送到和x同一device中： ```python x = x.flatten(2).transpose(1, 2) x = self.linear_proj(x) boi = self.boi.expand(x.shape[0],...
@yaoyingzhang @534114658 https://github.com/PaddlePaddle/FastDeploy/issues/1872 可以看一下这个