phoenares

Results 8 comments of phoenares

现在已经定位到是torch.matmul的问题,加了这个后,原本正常的模型也报segmentation fault了。调用代码如下: def inference_v2(): """ inference mobilenet_v1 using a specific picture """ interpreter = MNN.Interpreter("lstr.mnn") interpreter.setCacheFile('.tempcache') config = {} config['precision'] = 'low' print ('create sess') session = interpreter.createSession() print ('create...

@EEeEhh 欠拟合怎么理解啊老哥,我测试了3个模型,最小的模型把trainable设置为True之后,mAP 上升了,其余两个大一点的模型,都下降了

> @phoenares 要解决这个问题其实很简单,要么训练的时候就不要用ExponentialMovingAverage(效果有限),这样就可以达到“实时美颜”的效果;要么在上面我画出的evaluate.py文件中的代码,去掉Saver括号里面的代码。 我试一下,感谢

我现在测试ckpt和pb文件指标可以对齐了。加载模型的时候用不用ExponentialMovingAverage会有一点影响,在我这里是1个多点的影响。我这边主要是把image_demo.py里BGR转RGB那行去掉了,因为在utils.image_preprocess里做过了

第一个模型只是在第二个模型的基础上加了几个anchor

> see the picture for better understanding. Please explain the results to me > ![model](https://user-images.githubusercontent.com/28862708/66450552-8ee16280-ea8b-11e9-99f5-88ac8c8bd229.png) The line before 'Iteration 850...' you can find two 'recall',recall is calculated with IOU threshold...

@MuhammadAsadJaved test.sh: caffe train --solver solver.prototxt --weights XXX.caffemodel this is my solver.prototxt train_net: "models/yolov3_coco/sh2_0.5_yolo3_lite_train_simple_m3_gray_ft.prototxt" test_net: "models/yolov3_coco/sh2_0.5_yolo3_lite_test_m3_gray_ft.prototxt" test_iter: 500 test_interval: 1 base_lr: 0.01 display: 20 max_iter: 0 lr_policy: "multistep" gamma: 0.1...

could you tell more about how to transfer darknet weights to h5 file, I need use other weights file, thanks