zhangfeng13
zhangfeng13
Hi, i successed in training the model using 300w which contain about 4k images. but when i do data-argument(including rotation and offset faceRect),the images from 4K to 100k. and when...
你好,请问下,训练的h5文件对应的是该图片的 xmin ymin xmax ymax x1 y1 x2 y2 .....x68, 68吗? 多谢了,想自己学习训练下
# 平台: Windows10 # Github版本: **最新版本,82630820c04402e6282e7c717c4fc531c23808e2 (20211209) ** # 编译方式: - 0、选择vs2019的x64-NativeTools - 1、 powershell schema\generate.ps1 - 2、 mkdir build ; cd build - 3、cmake -G "NMake Makefiles" -DCMAKE_BUILD_TYPE=Release .....
方法的准确性
您好,看代码方法好像是直接从pretrain找了个模型,然后修改输出类别为101,然后做一个简单的分类,这个是不是效果不会很好。需要做什么特殊的处理吗~。
你好,模型中的V设置为101,是因为训练数据最大的年龄是101吗。如果自己的数据集,是不是也需要进行相应的调整
Hi i retrain the mobiliNet+SSD using voc0712 , after 25000 iters, mAp is 0.724 and loss decrease ~2.0 but when i using python demo.py after merge_bn.py ,the result is poor..like...
Hi the 68pts model is over 150M, i see the other luoyet-3000fps only 35M ,Why is there such a big difference
train data: glint360Datasets(https://github.com/deepinsight/insightface/blob/master/recognition/partial_fc/README.md); 1、 First,train baseline model with R50-Softmax 2、Second,Train ArcFace-Softmax by finetune the backbone using Step1 Backbone model . the acc is lower then origin softmax; 
您好,这边测试了一个weights/checkpoint_VOC_efficientdet-d1_37.pth的模型,结果是这个样子的,有几个好像未检测到 