zhang-qiang-github
zhang-qiang-github
I input two contours to `Ribbon` to generate a surface. The two contours are closed, but the `Ribbon` generated surface is not closed. The result is:  The red tube...
If there is a line and a mask, how can I obtain the intersection point? For example: mask = np.zeros([300, 300, 50]) mask[:, :, 10:30] = 1 Then, the line...
When analysis 3D image data by rendering, some tissue is unconcerned and it would distrub the analysis. Thus, I want to crop the image by a free-hand ROI just like...
If the original image is (H, W), the output of this segmentation is (H/4, W/4). If I want to obtain the segmentation result of (H, W), I need to upsampling...
在现在的网络中，输出一个概率p，和价值v。假设现在可以走的地方有10个选择，那么p是一个1*10的数，表示下一步在这10个位置下的概率，v是一个1*1的标量，表示赢的可能性。 我不是很理解这个v这个值的意思。如果v是对应着下一步的概率，那么它应该也是1*10的才对吧？这样才能表示下一步，下到10个位置输赢的可能性。现在只有1*1的东西，那么它表示啥意思？表示还没有下一步的时候的输赢？
The mask means the pixel inside of object is 1, and the pixel outside of object is 0. If I have a 3D binary mask, how can I create the...
Thanks for sharing this project. I use the high resolution DIV2K for this project, including 800 training pictures and 100 validation pictures. Then, the high resolution picture is downsampled by...
Thank you for sharing this project. I run the cifar10_test.py with the default configuration, and the accuracy of training data is about 50% for top 1and 90% for top 5....
Thank you for sharing this project code, and I have a question for nn.Embedding. In this project, the shape of `src` and `trg` is (maxLen, batch size). The forward of...
In the TransBTS_downsample8x_skipconnection.TransformerBTS: ``` self.Unet = Unet(in_channels=4, base_channels=16, num_classes=4) ``` This code would force the input has 4 channel. I think it should be modified as: ``` self.Unet = Unet(in_channels=num_channels,...