anchitdharmw
commented
3 years ago Hi @cuixing158, The mask-rcnn in the example is trained on 800x800x3 images. One recommendation here could be trying out a smaller image size.
Closed cuixing158 closed 3 years ago
anchitdharmw
commented
3 years ago Hi @cuixing158, The mask-rcnn in the example is trained on 800x800x3 images. One recommendation here could be trying out a smaller image size.
Even if batchsize=1, the out of memory error still occurs. My basic configuration is as follows: gpu: GTX1070-8g matlab2020b Changing to resnet50 backbone also does not work !
Error using nnet.internal.cnn.dlnetwork/forward (line 254) Layer 'res5b': Invalid input data. Out of memory on device. To view more detail about available memory on the GPU, use 'gpuDevice()'. If the problem persists, reset the GPU by calling 'gpuDevice(1)'. Error in nnet.internal.cnn.dlnetwork/CodegenOptimizationStrategy/propagateWithFallback (line 103) [varargout{1:nargout}] = fcn(net, X, layerIndices, layerOutputIndices); Error in nnet.internal.cnn.dlnetwork/CodegenOptimizationStrategy/forward (line 52) [varargout{1:nargout}] = propagateWithFallback(strategy, functionSlot, @forward, net, X, layerIndices, layerOutputIndices); Error in dlnetwork/forward (line 347) [varargout{1:nargout}] = net.EvaluationStrategy.forward(net.PrivateNetwork, x, layerIndices, layerOutputIndices); Error in networkGradients (line 22) [YRPNRegDeltas, proposal, YRCNNClass, YRCNNReg, YRPNClass, YMask, state] = forward(... Error in deep.internal.dlfeval (line 18) [varargout{1:nout}] = fun(x{:}); Error in dlfeval (line 41) [varargout{1:nout}] = deep.internal.dlfeval(fun,varargin{:});