deeplabv3
deeplabv3 copied to clipboard
fregu856
PyTorch implementation of DeepLabV3, trained on the Cityscapes dataset.
I don't find the weight file 'class_weights.pkl',can you tell me have to get it
Using a random cropping method, what is the difference between training and testing？
when i use resnet50-152 as the backbone to evaluate on my datasets , the shape doesn't match?
https://github.com/fregu856/deeplabv3/blob/415d983ec8a3e4ab6977b316d8f553371a415739/model/deeplabv3.py#L16 hello! i have a question in this line, why you use 20classes ? not 19 classes
https://github.com/fregu856/deeplabv3/blob/415d983ec8a3e4ab6977b316d8f553371a415739/datasets.py#L74 In get_item, you resize image to 50% of original dimensions. Then, you randomly scale downscaled image to 70-200%. In the case of upsamplig to 200%, information about original image...
Hi I have a question about the models. In the name you specify which ResNet you are using (how many layers) but also "OS_X". Looking at the code it seems...
i train my own module,but train loss decrease to 0.17 and stop decreasing,what about yours
Hi, How can I input a random sidewalk image and output a segmented image based on this model, after cloning your repository? Thanks, Jacob
