Error in train_flickr_word2_1_pool.m

[yurii-piets]

Hi I was following your instructions from Readme but while executing train_flickr_word2_1_pool.m appeared an error and I have no idea how to deal with it. Can you please help me? Error description:

>> train_flickr_word2_1_pool
cnn_train_dag: resetting GPU

ans = 

  CUDADevice with properties:

                      Name: 'GeForce RTX 2060'
                     Index: 1
         ComputeCapability: '7.5'
            SupportsDouble: 1
             DriverVersion: 10.1000
            ToolkitVersion: 8
        MaxThreadsPerBlock: 1024
          MaxShmemPerBlock: 49152
        MaxThreadBlockSize: [1024 1024 64]
               MaxGridSize: [2.1475e+09 65535 65535]
                 SIMDWidth: 32
               TotalMemory: 6.2228e+09
           AvailableMemory: 5.5524e+09
       MultiprocessorCount: 30
              ClockRateKHz: 1200000
               ComputeMode: 'Default'
      GPUOverlapsTransfers: 1
    KernelExecutionTimeout: 1
          CanMapHostMemory: 1
           DeviceSupported: 1
            DeviceSelected: 1

train: epoch 01:   1/253:Error using vl_nnconv
The FILTERS depth does not divide the DATA depth.

Error in dagnn.Conv/forward (line 12)
      outputs{1} = vl_nnconv(...

Error in dagnn.Layer/forwardAdvanced (line 85)
      outputs = obj.forward(inputs, {net.params(par).value}) ;

Error in dagnn.DagNN/eval (line 91)
  obj.layers(l).block.forwardAdvanced(obj.layers(l)) ;

Error in cnn_train_dag>processEpoch (line 222)
      net.eval(inputs, params.derOutputs, 'holdOn', s < params.numSubBatches) ;

Error in cnn_train_dag (line 90)
    [net, state] = processEpoch(net, state, params, 'train',opts) ;

Error in train_flickr_word2_1_pool (line 39)
[net,info] = cnn_train_dag(net, imdb, @getBatch,opts) ;

[yurii-piets]

Actually, I am experiencing the same error using train_coco_word2_1_pool.

[layumi]

HI @yurii-piets

Could you print the input data shape? And check whether it is consistent with the filter shape in the first conv layer.

The problem looks like the case that the shape is not consistent in the input data and first conv layer.