SimJeg / FC-DenseNet

Fully Convolutional DenseNets for semantic segmentation.
487 stars 143 forks source link

test.py in line:I, U, acc = f(X, Y[:, None, :, :])error? #30

Open andongchen opened 7 years ago

andongchen commented 7 years ago

Hi, I have fixed many problems at load_data now. but, how can i fix this error in test.py in line:I, U, acc = f(X, Y[:, None, :, :])error? thank you very much

Traceback (most recent call last): File "/home/chenandong/FC-DenseNet/test.py", line 95, in test(config_path, weight_path) File "/home/chenandong/FC-DenseNet/test.py", line 70, in test I, U, acc = f(X, Y[:, None, :, :]) File "/usr/local/lib/python2.7/dist-packages/theano/compile/function_module.py", line 871, in call storage_map=getattr(self.fn, 'storage_map', None)) File "/usr/local/lib/python2.7/dist-packages/theano/gof/link.py", line 314, in raise_with_op reraise(exc_type, exc_value, exc_trace) File "/usr/local/lib/python2.7/dist-packages/theano/compile/function_module.py", line 859, in call outputs = self.fn() ValueError: CorrMM received weight with wrong type. Apply node that caused the error: CorrMM{half, (1, 1)}(input_var, W) Toposort index: 18 Inputs types: [TensorType(float32, 4D), TensorType(float64, 4D)] Inputs shapes: [(10, 3, 360, 480), (48, 3, 3, 3)] Inputs strides: [(2073600, 691200, 1920, 4), (216, 72, 24, 8)] Inputs values: ['not shown', 'not shown'] Outputs clients: [[Elemwise{add,no_inplace}(CorrMM{half, (1, 1)}.0, InplaceDimShuffle{x,0,x,x}.0)]]