chenjiafu-George

Results 43 comments of chenjiafu-George

使用自定义的数据集运行时，每次都是这两个损失为0， loss_bbox: 0.0000 和 loss_dfl:0.0000

> > 确保测试"num_classes=你的类别数"，然后检查text json包括类别，有没有设置正确。 > > 类别设置的是7类 num_classes = 7 num_training_classes = 7 > > text json设置的是 [["1"],["missing_hole"], ["mouse_bite"], ["open_circuit"], ["short"], ["spur"],["spurious_copper"]] Hi @tm924222 ，我之前也遇到过这个问题，你需要检查你class的语法问题，类似于[["missing_hole"], ["mouse_bite"], ["open_circuit"], ["short"], ["spur"],["spurious_copper"]],一个类别需要有一个方框，并且在训练集配置和验证集配置中添加metainfo信息，类似于这个样子： `classes...

使用自定义的数据集运行时，每次都是这两个损失为0， loss_bbox: 0.0000 和 loss_dfl:0.0000

> > > > 确保测试"num_classes=你的类别数"，然后检查text json包括类别，有没有设置正确。 > > > > > > > > > 类别设置的是7类 num_classes = 7 num_training_classes = 7 > > > text json设置的是 [["1"],["missing_hole"], ["mouse_bite"], ["open_circuit"],...

About the problem that after quantizing the model, the model cannot reason and the accuracy is greatly reduced.

> 你好@chenjiafu-George，您需要检查： > > 1. 训练期间使用的图像分辨率。如果你想使用 进行推断`1280x384`，你最好加载预训练的模型并微调 YOLO-World 的`1280x384`分辨率， > 2. 后处理，看起来结果有偏移。 Hi @wondervictor ,I did modify the input_size 1280x384 in the training of the problem you said, and the...

About the problem that after quantizing the model, the model cannot reason and the accuracy is greatly reduced.

> 你好@chenjiafu-George，您需要检查： > > 1. 训练期间使用的图像分辨率。如果你想使用 进行推断`1280x384`，你最好加载预训练的模型并微调 YOLO-World 的`1280x384`分辨率， > 2. 后处理，看起来结果有偏移。 Hi @wondervictor ,for your reply 2, aboat the postprocessing, it seems that the results have offsets. This may...

About the problem that after quantizing the model, the model cannot reason and the accuracy is greatly reduced.

> 你好@chenjiafu-George，您需要`--custom-texts`在导出过程中指定。如果您想使用 TFLite 量化模型，则需要额外的`--without-bbox-decoder`.您可以参考：https://github.com/AILab-CVC/YOLO-World/blob/master/docs/tflite_deploy.md Hi @wondervictor, Sorry to bother you so late. Yes, I do use such argument, but I have only exported model 1 KB, I tried many times...

About the problem that after quantizing the model, the model cannot reason and the accuracy is greatly reduced.

> Have you used the latest code, including `easydeploy`? Hi @wondervictor I'm using the latest version of easydeploy. After use, it is indeed 1kb. I tried to switch back to...

About the problem that after quantizing the model, the model cannot reason and the accuracy is greatly reduced.

> Have you used the latest code, including `easydeploy`? Hi @wondervictor ,Is there a problem with the Clip version? When I ran the previous version, this message didn't appear. I...

About the problem that after quantizing the model, the model cannot reason and the accuracy is greatly reduced.

Hi @wondervictor ,I'm sorry to disturb you. I pulled the project code again and tried again. Now the problem has been solved, and the problem may be caused by the...

About the problem that after quantizing the model, the model cannot reason and the accuracy is greatly reduced.

> Have you quantized YOLO-World with TFLite? You can try the [tflite demo](https://github.com/AILab-CVC/YOLO-World/blob/master/deploy/tflite_demo.py) here. Notably, TFLite does not support GPU which is more suitable for mobile/edge devices. Hi @wondervictor ,Yes,...

About the problem that after quantizing the model, the model cannot reason and the accuracy is greatly reduced.

> Have you quantized YOLO-World with TFLite? You can try the [tflite demo](https://github.com/AILab-CVC/YOLO-World/blob/master/deploy/tflite_demo.py) here. Notably, TFLite does not support GPU which is more suitable for mobile/edge devices. Hi @wondervictor ,What...