Retinanet-Pytorch icon indicating copy to clipboard operation
Retinanet-Pytorch copied to clipboard

Retinanet目标检测算法(简单,明了,易用,全中文注释,单机多卡训练,视频检测)(based on pytorch,Simple, Clear, Mutil GPU)

Results 20 Retinanet-Pytorch issues
Sort by recently updated
recently updated
newest added

请问您有在voc上完整训练吗,最后的mAP大概有多少呀

嗨喽大佬你好正在学习你的代码,fpn.py里最后的3*3卷积都是用的self.top_down_conv1吗?这样就共享权重了?那上面怎么还定义了conv2和conv3呢?求大佬的解答

--- load weight finish --- Setting up a new session... Max_iter = 120000, Batch_size = 20 Model will train on cuda:[0] --- Focal_loss alpha = 0.25 ,将对背景类进行衰减,请在目标检测任务中使用 --- --- Multiboxloss...

Traceback (most recent call last): File "F:/Retinanet-Pytorch-master/Demo_train.py", line 36, in trainer(net, train_dataset) File "F:\Retinanet-Pytorch-master\Model\trainer.py", line 115, in __call__ reg_loss, cls_loss = self.loss_func(cls_logits, bbox_preds, labels, boxes) File "D:\anaconda3\envs\pytorch\lib\site-packages\torch\nn\modules\module.py", line 547, in...

您好,非常感谢您的代码。我尝试将您的focal loss部分加到retinaface模型中,没有改动参数,发现误检特别多。想问下知道可能的原因嘛?是因为我没有进行hard negative mining还是因为我参数没有调对呢?(尝试过修改阈值但作用非常微小)

谢谢提供这个模型,由于我修改了FPN的结构,在训练的时候(8G的显存),输入尺寸为600时,总是出现CUDA out of memory,我想减小到输入尺寸为300,特征图(5层)应该变成 38、19、10、5、3,那么对应的预测框大小该如何设置?