search

hellochick / PSPNet-tensorflow

TensorFlow-based implementation of "Pyramid Scene Parsing Network".
326 stars 123 forks source link

small size #68

Open mxkai opened 5 years ago

mxkai commented 5 years ago

Can I use the pre-training model to calculate the miou and mean Pixel Accuracy of a small-sized image, such as 128*256

mxkai commented 5 years ago

I wanted to evaluate small-scale images, but there was a problem： could not convert BatchDescriptor {count: 1 feature_map_count: 2048 spatial: 0 1 value_min: 0.000000 value_max: 0.000000 layout: BatchDepthYX} to cudnn tensor descriptor: CUDNN_STATUS_BAD_PARAM

Please let me know if anyone knows the solution