search

junjiehe96 / FastInst

[CVPR2023] FastInst: A Simple Query-Based Model for Real-Time Instance Segmentation
MIT License
182 stars 17 forks source link

Not able to Classify the dataset #46

Open arunsandy1309 opened 6 months ago

arunsandy1309 commented 6 months ago

Hello,

I'm trying to implement this model on my own dataset which has 6 diferent types of objects and I need to perform instance segmentation on them.. I'm currently using Resnet101 architecture and SGD optimizer with LR 0.0001. Even though I trained the model for 1Lakh epoch, the model is not able to classify the images image

Can you please let me know what might be the possible error I made while training.

niuma345 commented 6 months ago

你好

我正在尝试在我自己的数据集上实现此模型，该数据集具有 6 种不同类型的对象，我需要对它们执行实例分割。我目前正在使用 LR 0.0001 的 Resnet101 架构和 SGD 优化器。即使我训练了 10 万纪元的模型，该模型也无法对图像进行分类 图像

你能告诉我我在训练时可能犯的错误是什么吗？

请问这个问题您解决了吗

niuma345 commented 6 months ago

Hello,

I'm trying to implement this model on my own dataset which has 6 diferent types of objects and I need to perform instance segmentation on them.. I'm currently using Resnet101 architecture and SGD optimizer with LR 0.0001. Even though I trained the model for 1Lakh epoch, the model is not able to classify the images image

Can you please let me know what might be the possible error I made while training.

你好，请问你可以加载自己的数据集吗，我也是做实例分割，建立了自己的coco数据集，但是一直报“matrix contains invalid numeric entries”错误