semantic-segmentation

问题 I'm trying to implement SegNet in Keras (tf backend) to do semantic segmentation. The most impressived trick of SgeNet is to pass max-pooling indices to the upsampling layers. However, there are many implementations of SegNet in Keras(e.g.) I find on github just using simple UpSampling (called SegNet-Basic). I notice that it can be achieved in Tensorflow with " tf.nn.max_pool_with_argmax ". So I want to know is there any similar method to get the max-pooling indices and put them back in

问题 I am trying to implement a paper on Semantic Segmentation and I am confused about how to Upsample the prediction map produced by my segmentation network to match the input image size. For example, I am using a variant of Resnet101 as the segmentation network (as used by the paper). With this network structure, an input of size 321x321 (again used in the paper) produces a final prediction map of size 41x41xC (C is the number of classes). Because I have to make pixel-level predictions, I need

问题 I am trying to implement a paper on Semantic Segmentation and I am confused about how to Upsample the prediction map produced by my segmentation network to match the input image size. For example, I am using a variant of Resnet101 as the segmentation network (as used by the paper). With this network structure, an input of size 321x321 (again used in the paper) produces a final prediction map of size 41x41xC (C is the number of classes). Because I have to make pixel-level predictions, I need

问题 I'm training a semantic segmentation model using Keras with TensorFlow backend. I adopted ImageDataGenerator to do the image augmentation, including rotation, flip and shift. By following the documentation, I created a dictionary maskgen_args and used it as arguments to instantiate two ImageDataGenerator instances. maskgen_args = dict( rotation_range=90, validation_split=VALIDATION_SPLIT ) image_datagen = ImageDataGenerator(**maskgen_args) mask_datagen = ImageDataGenerator(**maskgen_args) The

问题 I am new to Synthia dataset. I would like to read the label file from this datset. I expect to have one channel matrix with size of my RGB image, but when I load the data I got 3x760x1280 and it is full of zeros. I tried to read as belows: label = np.asarray(imread(label_path)) Can anyone help to read these labels file correctly? 回答1: I found the right way to read it as below: label = np.asarray(imageio.imread(label_path, format='PNG-FI'))[:,:,0] 来源： https://stackoverflow.com/questions

问题 I am doing an image segmentation task. There are 7 classes in total so the final outout is a tensor like [batch, 7, height, width] which is a softmax output. Now intuitively I wanted to use CrossEntropy loss but the pytorch implementation doesn't work on channel wise one-hot encoded vector So I was planning to make a function on my own. With a help from some stackoverflow, My code so far looks like this from torch.autograd import Variable import torch import torch.nn.functional as F def cross

问题 I am doing an image segmentation task. There are 7 classes in total so the final outout is a tensor like [batch, 7, height, width] which is a softmax output. Now intuitively I wanted to use CrossEntropy loss but the pytorch implementation doesn't work on channel wise one-hot encoded vector So I was planning to make a function on my own. With a help from some stackoverflow, My code so far looks like this from torch.autograd import Variable import torch import torch.nn.functional as F def cross

问题 I am doing an image segmentation task. There are 7 classes in total so the final outout is a tensor like [batch, 7, height, width] which is a softmax output. Now intuitively I wanted to use CrossEntropy loss but the pytorch implementation doesn't work on channel wise one-hot encoded vector So I was planning to make a function on my own. With a help from some stackoverflow, My code so far looks like this from torch.autograd import Variable import torch import torch.nn.functional as F def cross

问题 I want to perform instance segmentation using SSD model. For this, I have used an FCN model to perform instance segmentation and now can I combine this with SSD model to get something like Mask SSD ? It should look something like this or something like this 来源： https://stackoverflow.com/questions/61734815/how-to-combine-a-fully-convolutional-neural-network-with-a-ssd-mobilenet-model

问题 I am trying to get point level segmentation from box annotations. I get the box annotation in the form of a Json File from online labeling software Supervisely. I use PCL's cropbox filter to obtain a point level segmentation. Although, most of the points are correctly being obtained, I am still getting indices of points outside the box. I think there is something going wrong with how I am assigning the orientation of box in the filter. The methodology is discussed in a previous stack overflow