-
# error
```
(new) ➜ deeplab git:(master) sh test/train.sh
current path is /home/yzbx/git/deeplab
/home/yzbx/bin/miniconda3/envs/new/lib/python3.6/site-packages/h5py/__init__.py:36: FutureWarning…
-
https://github.com/jfzhang95/pytorch-deeplab-xception/blob/master/modeling/backbone/xception.py
https://github.com/jfzhang95/pytorch-deeplab-xception/blob/master/doc/deeplab_xception.py
In above pty…
-
我试过解冻和不解冻 也改过优化器 最终的miou都是72左右 3090 和2080 都试过 一直跑不出作者的76.8 大家有尝试过吗 请教一下
`----------------------------------------------------------------------
| keys | …
-
Training the model after adjustments were made to the training data, using the best model as base model.
-
使用xception作为主干网络。
哥，对于您写的代码：
1、当pretrained=True 且model_path="model_data/xception_pytorch_imagenet.pth"
2、当pretrained=False且model_path="model_data/xception_pytorch_imagenet.pth"
3、当pretrained=Tru…
-
@stonessss yes, i write test code.
1. copy and overwrite.
https://github.com/jaemin93/pytorch-deeplab-xception/blob/master/test.py
https://github.com/jaemin93/pytorch-deeplab-xception/blob/master…
-
Hi Caleb,
Thank you so much for the detailed explanation on how to preprocess the images for VGG and ResNet to reproduce the Keras Top1/5s. I used your preprocessing method and got almost identical…
-
Hi, I am looking to visualize the activations layers for a given image for tiny yolov3.
Example : https://medium.com/google-developer-experts/interpreting-deep-learning-models-for-computer-vision-…
-
Traceback (most recent call last):
File "train.py", line 340, in
trainer = Trainer(args)
File "train.py", line 167, in __init__
aux=args.aux, norm_layer=BatchNorm2d).to(self.device)
…
-
您好，我搜索到您是中国人，所以我用汉语提问了。
我用您提供的代码test了我的数据集，我用的pretrained_model是ffpp_c23.pth，准确率是78%，我用deepfake_c0_xception.pkl，准确率是73%。这是最高的准确率了。
我尝试冻结模型的前十个block，在deepfake_c0_xception.pkl上继续训练，训练集达到了1.但是测试集是20%多，我…