search

CodeMonsterPHD / GaTector-A-Unified-Framework-for-Gaze-Object-Prediction

This repository is the official implementation of GaTector, which studies the newly proposed task, gaze object prediction. In this work, we build a novel framework named GaTector to tackle the gaze object prediction problem in a unified way. Particularly, a specific-general-specific (SGS) feature extractor is firstly proposed to utilize a shared backbone to extract general features for both scene and head images. To better consider the specificity of inputs and tasks, SGS introduces two input-specific blocks before the shared backbone and three task-specific blocks after the shared backbone. Specifically, a novel defocus layer is designed to generate object-specific features for object detection task without losing information or requiring extra computations. Moreover, the energy aggregation loss is introduced to guide the gaze heatmap to concentrate on the stared box. In the end, we propose a novel mDAP metric that can reveal the difference between boxes even when they share no overlapping area. Extensive experiments on the GOO dataset verify the superiority of our method in all three tracks, i.e., object detection, gaze estimation, and gaze object prediction.
https://arxiv.org/abs/2112.03549
64 stars 11 forks source link

Training error #2

Open yyyyzy1 opened 1 year ago

yyyyzy1 commented 1 year ago

In the first round of training,there was a error''int' object has no attribute' in file 'utils_fit.py',line 87,in fit_one_epoch

huTao1030 commented 1 year ago

In the first round of training,there was a error''int' object has no attribute' in file 'utils_fit.py',line 87,in fit_one_epoch

Can you describe in more detail the problem you're encountering? Lines 86-89 are mainly used to record log files. You can try to delete it without affecting the training.

yyyyzy1 commented 1 year ago

In the first round of training,there was a error''int' object has no attribute' in file 'utils_fit.py',line 87,in fit_one_epoch

Can you describe in more detail the problem you're encountering? Lines 86-89 are mainly used to record log files. You can try to delete it without affecting the training.

非常感谢您的回复！我还想请教您一些问题，pre_train模型是放在那个地方使用呢？另外，进行可视化操作的文件是predict_yolo.py文件吗？非常感谢！

huTao1030 commented 1 year ago

In the first round of training,there was a error''int' object has no attribute' in file 'utils_fit.py',line 87,in fit_one_epoch

Can you describe in more detail the problem you're encountering? Lines 86-89 are mainly used to record log files. You can try to delete it without affecting the training.

非常感谢您的回复！我还想请教您一些问题，pre_train模型是放在那个地方使用呢？另外，进行可视化操作的文件是predict_yolo.py文件吗？非常感谢！

预训练模型可以放在任意位置，但是需要修改代码中载入权重时的相对路径。另外predict_yolo.py是单独对目标检测分支的结果进行可视化。 如果还有什么疑问，欢迎提问。

yyyyzy1 commented 1 year ago

In the first round of training,there was a error''int' object has no attribute' in file 'utils_fit.py',line 87,in fit_one_epoch

Can you describe in more detail the problem you're encountering? Lines 86-89 are mainly used to record log files. You can try to delete it without affecting the training.

非常感谢您的回复！我还想请教您一些问题，pre_train模型是放在那个地方使用呢？另外，进行可视化操作的文件是predict_yolo.py文件吗？非常感谢！

预训练模型可以放在任意位置，但是需要修改代码中载入权重时的相对路径。另外predict_yolo.py是单独对目标检测分支的结果进行可视化。 如果还有什么疑问，欢迎提问。

非常感谢老师您的回复！我现在已经把整体大致跑出来了，但是还不太明白怎么进行论文里gaze estimation（GE）、gaze object prediction（GOD）的可视化，请问老师您的代码中有这部分的可视化操作吗？再次感谢老师！

huTao1030 commented 1 year ago

目前版本中并未包含GE和GOD的可视化代码，如果有需要你可以尝试利用GE部分输出的heatmap作为蒙版进行相关的可视化。

In the first round of training,there was a error''int' object has no attribute' in file 'utils_fit.py',line 87,in fit_one_epoch

Can you describe in more detail the problem you're encountering? Lines 86-89 are mainly used to record log files. You can try to delete it without affecting the training.

非常感谢您的回复！我还想请教您一些问题，pre_train模型是放在那个地方使用呢？另外，进行可视化操作的文件是predict_yolo.py文件吗？非常感谢！

预训练模型可以放在任意位置，但是需要修改代码中载入权重时的相对路径。另外predict_yolo.py是单独对目标检测分支的结果进行可视化。 如果还有什么疑问，欢迎提问。

非常感谢老师您的回复！我现在已经把整体大致跑出来了，但是还不太明白怎么进行论文里gaze estimation（GE）、gaze object prediction（GOD）的可视化，请问老师您的代码中有这部分的可视化操作吗？再次感谢老师！

目前版本中并未包含GE和GOD的可视化代码，你可以尝试利用GE部分输出的heatmap作为蒙版进行相关的可视化操作。我们也会再后续的工作中对开源的代码进行整理完善。

yyyyzy1 commented 1 year ago

目前版本中并未包含GE和GOD的可视化代码，如果有需要你可以尝试利用GE部分输出的heatmap作为蒙版进行相关的可视化。

In the first round of training,there was a error''int' object has no attribute' in file 'utils_fit.py',line 87,in fit_one_epoch

Can you describe in more detail the problem you're encountering? Lines 86-89 are mainly used to record log files. You can try to delete it without affecting the training.

非常感谢您的回复！我还想请教您一些问题，pre_train模型是放在那个地方使用呢？另外，进行可视化操作的文件是predict_yolo.py文件吗？非常感谢！

预训练模型可以放在任意位置，但是需要修改代码中载入权重时的相对路径。另外predict_yolo.py是单独对目标检测分支的结果进行可视化。 如果还有什么疑问，欢迎提问。

非常感谢老师您的回复！我现在已经把整体大致跑出来了，但是还不太明白怎么进行论文里gaze estimation（GE）、gaze object prediction（GOD）的可视化，请问老师您的代码中有这部分的可视化操作吗？再次感谢老师！

目前版本中并未包含GE和GOD的可视化代码，你可以尝试利用GE部分输出的heatmap作为蒙版进行相关的可视化操作。我们也会再后续的工作中对开源的代码进行整理完善。

老师，您好！非常感谢您的回复，在您写的readme中提到：When you training the model, the index of gaze will be saved in gaze_performence.txt，但是当我train_mode=0的时候并没有这个txt文件生成，只有包含AUC,Dist,Ang的performance.csv文件，没有预测的目标结果txt，请问这是怎么回事呢？