2016-05-18 13 views
6

Viene visualizzato un errore durante l'esecuzione dell'app di test. (quando sto usando un modello addestrato con la mia applicazione di prova)Errore Caffe Impossibile copiare il parametro 0 pesi dal livello, mancata corrispondenza di forma

F0518 18:21:13.978204 13437 net.cpp:766] Cannot copy param 0 weights from layer 'fc6'; shape mismatch. Source param shape is 4096 2304 (9437184); target param shape is 4096 9216 (37748736). To learn this layer's parameters from scratch rather than copying from a saved net, rename the layer. 
*** Check failure stack trace: *** 
Aborted (core dumped) 

Qualcuno può dire il motivo di ciò?


deploy.prototxt


name: "CaffeNet" 
layer { 
    name: "data" 
    type: "Input" 
    top: "data" 
    input_param { shape: { dim: 10 dim: 3 dim: 227 dim: 227 } } 
} 
layer { 
    name: "conv1" 
    type: "Convolution" 
    bottom: "data" 
    top: "conv1" 
    convolution_param { 
    num_output: 96 
    kernel_size: 11 
    stride: 4 
    } 
} 
layer { 
    name: "relu1" 
    type: "ReLU" 
    bottom: "conv1" 
    top: "conv1" 
} 
layer { 
    name: "pool1" 
    type: "Pooling" 
    bottom: "conv1" 
    top: "pool1" 
    pooling_param { 
    pool: MAX 
    kernel_size: 3 
    stride: 2 
    } 
} 
layer { 
    name: "norm1" 
    type: "LRN" 
    bottom: "pool1" 
    top: "norm1" 
    lrn_param { 
    local_size: 5 
    alpha: 0.0001 
    beta: 0.75 
    } 
} 
layer { 
    name: "conv2" 
    type: "Convolution" 
    bottom: "norm1" 
    top: "conv2" 
    convolution_param { 
    num_output: 256 
    pad: 2 
    kernel_size: 5 
    group: 2 
    } 
} 
layer { 
    name: "relu2" 
    type: "ReLU" 
    bottom: "conv2" 
    top: "conv2" 
} 
layer { 
    name: "pool2" 
    type: "Pooling" 
    bottom: "conv2" 
    top: "pool2" 
    pooling_param { 
    pool: MAX 
    kernel_size: 3 
    stride: 2 
    } 
} 
layer { 
    name: "norm2" 
    type: "LRN" 
    bottom: "pool2" 
    top: "norm2" 
    lrn_param { 
    local_size: 5 
    alpha: 0.0001 
    beta: 0.75 
    } 
} 
layer { 
    name: "conv3" 
    type: "Convolution" 
    bottom: "norm2" 
    top: "conv3" 
    convolution_param { 
    num_output: 384 
    pad: 1 
    kernel_size: 3 
    } 
} 
layer { 
    name: "relu3" 
    type: "ReLU" 
    bottom: "conv3" 
    top: "conv3" 
} 
layer { 
    name: "conv4" 
    type: "Convolution" 
    bottom: "conv3" 
    top: "conv4" 
    convolution_param { 
    num_output: 384 
    pad: 1 
    kernel_size: 3 
    group: 2 
    } 
} 
layer { 
    name: "relu4" 
    type: "ReLU" 
    bottom: "conv4" 
    top: "conv4" 
} 
layer { 
    name: "conv5" 
    type: "Convolution" 
    bottom: "conv4" 
    top: "conv5" 
    convolution_param { 
    num_output: 256 
    pad: 1 
    kernel_size: 3 
    group: 2 
    } 
} 
layer { 
    name: "relu5" 
    type: "ReLU" 
    bottom: "conv5" 
    top: "conv5" 
} 
layer { 
    name: "pool5" 
    type: "Pooling" 
    bottom: "conv5" 
    top: "pool5" 
    pooling_param { 
    pool: MAX 
    kernel_size: 3 
    stride: 2 
    } 
} 
layer { 
    name: "fc6" 
    type: "InnerProduct" 
    bottom: "pool5" 
    top: "fc6" 
    inner_product_param { 
    num_output: 4096 
    } 
} 
layer { 
    name: "relu6" 
    type: "ReLU" 
    bottom: "fc6" 
    top: "fc6" 
} 
layer { 
    name: "drop6" 
    type: "Dropout" 
    bottom: "fc6" 
    top: "fc6" 
    dropout_param { 
    dropout_ratio: 0.5 
    } 
} 
layer { 
    name: "fc7" 
    type: "InnerProduct" 
    bottom: "fc6" 
    top: "fc7" 
    inner_product_param { 
    num_output: 4096 
    } 
} 
layer { 
    name: "relu7" 
    type: "ReLU" 
    bottom: "fc7" 
    top: "fc7" 
} 
layer { 
    name: "drop7" 
    type: "Dropout" 
    bottom: "fc7" 
    top: "fc7" 
    dropout_param { 
    dropout_ratio: 0.5 
    } 
} 
layer { 
    name: "fc8" 
    type: "InnerProduct" 
    bottom: "fc7" 
    top: "fc8" 
    inner_product_param { 
    num_output: 2 
    } 
} 
layer { 
    name: "prob" 
    type: "Softmax" 
    bottom: "fc8" 
    top: "prob" 
} 

train_val.prototxt


name: "CaffeNet" 
layer { 
    name: "data" 
    type: "Data" 
    top: "data" 
    top: "label" 
    include { 
    phase: TRAIN 
    } 
    transform_param { 
    mirror: true 
    crop_size: 256 
    mean_file: "data/lmvhmv/imagenet_mean.binaryproto" 
    } 
# mean pixel/channel-wise mean instead of mean image 
# transform_param { 
# crop_size: 126 
# mean_value: 104 
# mean_value: 117 
# mean_value: 123 
# mirror: true 
# } 
    data_param { 
    source: "examples/imagenet/lmvhmv1_train_lmdb" 
    batch_size: 10 
    backend: LMDB 
    } 
} 
layer { 
    name: "data" 
    type: "Data" 
    top: "data" 
    top: "label" 
    include { 
    phase: TEST 
    } 
    transform_param { 
    mirror: false 
    crop_size: 256 
    mean_file: "data/ilsvrc12/imagenet_mean.binaryproto" 
    } 
# mean pixel/channel-wise mean instead of mean image 
# transform_param { 
# crop_size: 256 
# mean_value: 104 
# mean_value: 117 
# mean_value: 123 
# mirror: true 
# } 
    data_param { 
    source: "examples/imagenet/lmvhmv1_test_lmdb" 
    batch_size: 10 
    backend: LMDB 
    } 
} 
layer { 
    name: "conv1" 
    type: "Convolution" 
    bottom: "data" 
    top: "conv1" 
    param { 
    lr_mult: 1 
    decay_mult: 1 
    } 
    param { 
    lr_mult: 2 
    decay_mult: 0 
    } 
    convolution_param { 
    num_output: 96 
    kernel_size: 11 
    stride: 4 
    weight_filler { 
     type: "gaussian" 
     std: 0.01 
    } 
    bias_filler { 
     type: "constant" 
     value: 1 
    } 
    } 
} 
layer { 
    name: "relu1" 
    type: "ReLU" 
    bottom: "conv1" 
    top: "conv1" 
} 
layer { 
    name: "pool1" 
    type: "Pooling" 
    bottom: "conv1" 
    top: "pool1" 
    pooling_param { 
    pool: MAX 
    kernel_size: 3 
    stride: 2 
    } 
} 
layer { 
    name: "norm1" 
    type: "LRN" 
    bottom: "pool1" 
    top: "norm1" 
    lrn_param { 
    local_size: 5 
    alpha: 0.0001 
    beta: 0.75 
    } 
} 
layer { 
    name: "conv2" 
    type: "Convolution" 
    bottom: "norm1" 
    top: "conv2" 
    param { 
    lr_mult: 1 
    decay_mult: 1 
    } 
    param { 
    lr_mult: 2 
    decay_mult: 0 
    } 
    convolution_param { 
    num_output: 256 
    pad: 2 
    kernel_size: 5 
    group: 2 
    weight_filler { 
     type: "gaussian" 
     std: 0.01 
    } 
    bias_filler { 
     type: "constant" 
     value: 1 
    } 
    } 
} 
layer { 
    name: "relu2" 
    type: "ReLU" 
    bottom: "conv2" 
    top: "conv2" 
} 
layer { 
    name: "pool2" 
    type: "Pooling" 
    bottom: "conv2" 
    top: "pool2" 
    pooling_param { 
    pool: MAX 
    kernel_size: 3 
    stride: 2 
    } 
} 
layer { 
    name: "norm2" 
    type: "LRN" 
    bottom: "pool2" 
    top: "norm2" 
    lrn_param { 
    local_size: 5 
    alpha: 0.0001 
    beta: 0.75 
    } 
} 
layer { 
    name: "conv3" 
    type: "Convolution" 
    bottom: "norm2" 
    top: "conv3" 
    param { 
    lr_mult: 1 
    decay_mult: 1 
    } 
    param { 
    lr_mult: 2 
    decay_mult: 0 
    } 
    convolution_param { 
    num_output: 384 
    pad: 1 
    kernel_size: 3 
    weight_filler { 
     type: "gaussian" 
     std: 0.01 
    } 
    bias_filler { 
     type: "constant" 
     value: 1 
    } 
    } 
} 
layer { 
    name: "relu3" 
    type: "ReLU" 
    bottom: "conv3" 
    top: "conv3" 
} 
layer { 
    name: "conv4" 
    type: "Convolution" 
    bottom: "conv3" 
    top: "conv4" 
    param { 
    lr_mult: 1 
    decay_mult: 1 
    } 
    param { 
    lr_mult: 2 
    decay_mult: 0 
    } 
    convolution_param { 
    num_output: 384 
    pad: 1 
    kernel_size: 3 
    group: 2 
    weight_filler { 
     type: "gaussian" 
     std: 0.01 
    } 
    bias_filler { 
     type: "constant" 
     value: 1 
    } 
    } 
} 
layer { 
    name: "relu4" 
    type: "ReLU" 
    bottom: "conv4" 
    top: "conv4" 
} 
layer { 
    name: "conv5" 
    type: "Convolution" 
    bottom: "conv4" 
    top: "conv5" 
    param { 
    lr_mult: 1 
    decay_mult: 1 
    } 
    param { 
    lr_mult: 2 
    decay_mult: 0 
    } 
    convolution_param { 
    num_output: 256 
    pad: 1 
    kernel_size: 3 
    group: 2 
    weight_filler { 
     type: "gaussian" 
     std: 0.01 
    } 
    bias_filler { 
     type: "constant" 
     value: 1 
    } 
    } 
} 
layer { 
    name: "relu5" 
    type: "ReLU" 
    bottom: "conv5" 
    top: "conv5" 
} 
layer { 
    name: "pool5" 
    type: "Pooling" 
    bottom: "conv5" 
    top: "pool5" 
    pooling_param { 
    pool: MAX 
    kernel_size: 3 
    stride: 2 
    } 
} 
layer { 
    name: "fc6" 
    type: "InnerProduct" 
    bottom: "pool5" 
    top: "fc6" 
    param { 
    lr_mult: 1 
    decay_mult: 1 
    } 
    param { 
    lr_mult: 2 
    decay_mult: 0 
    } 
    inner_product_param { 
    num_output: 4096 
    weight_filler { 
     type: "gaussian" 
     std: 0.005 
    } 
    bias_filler { 
     type: "constant" 
     value: 1 
    } 
    } 
} 
layer { 
    name: "relu6" 
    type: "ReLU" 
    bottom: "fc6" 
    top: "fc6" 
} 
layer { 
    name: "drop6" 
    type: "Dropout" 
    bottom: "fc6" 
    top: "fc6" 
    dropout_param { 
    dropout_ratio: 0.5 
    } 
} 
layer { 
    name: "fc7" 
    type: "InnerProduct" 
    bottom: "fc6" 
    top: "fc7" 
    param { 
    lr_mult: 1 
    decay_mult: 1 
    } 
    param { 
    lr_mult: 2 
    decay_mult: 0 
    } 
    inner_product_param { 
    num_output: 4096 
    weight_filler { 
     type: "gaussian" 
     std: 0.005 
    } 
    bias_filler { 
     type: "constant" 
     value: 1 
    } 
    } 
} 
layer { 
    name: "relu7" 
    type: "ReLU" 
    bottom: "fc7" 
    top: "fc7" 
} 
layer { 
    name: "drop7" 
    type: "Dropout" 
    bottom: "fc7" 
    top: "fc7" 
    dropout_param { 
    dropout_ratio: 0.5 
    } 
} 
layer { 
    name: "fc8" 
    type: "InnerProduct" 
    bottom: "fc7" 
    top: "fc8" 
    param { 
    lr_mult: 1 
    decay_mult: 1 
    } 
    param { 
    lr_mult: 2 
    decay_mult: 0 
    } 
    inner_product_param { 
    num_output: 2 
    weight_filler { 
     type: "gaussian" 
     std: 0.01 
    } 
    bias_filler { 
     type: "constant" 
     value: 1 
    } 
    } 
} 
layer { 
    name: "accuracy" 
    type: "Accuracy" 
    bottom: "fc8" 
    bottom: "label" 
    top: "accuracy" 
    include { 
    phase: TEST 
    } 
} 
layer { 
    name: "loss" 
    type: "SoftmaxWithLoss" 
    bottom: "fc8" 
    bottom: "label" 
    top: "loss" 
} 
+0

Condividere il file di prototipo che è stato utilizzato per addestrare e testare per individuare il problema. Dovrebbe essere principalmente perché le dimensioni dell'immagine di input non sono le stesse sia nel prototipo di test sia nel prototipo del treno. Controllare l'altezza, la larghezza e il conteggio dei canali del test e del prototipo del treno –

+0

Sono stato in grado di addestrare correttamente il caffe, questo sta accadendo nell'applicazione di prova dove sto usando un modello di caffe preparato. – Deepak

+0

Ok, ora funziona quando ho corretto il valore di dim in deploy.txt mentre funziona – Deepak

risposta

9

La formazione è stato fatto su un'immagine di dimensione 256x256x3, ma il prototipo di prova tenta di leggere nell'immagine 227x227x3. I livelli convoluzionali non mostreranno alcun problema in quanto la dimensione dei BLOB di input sugli strati convoluzionali non ha importanza. I livelli completamente connessi si bloccano quando rileva che il BLOB di input ha una dimensione diversa. In altre parole, la dimensione dei pesi di un livello completamente connesso è correlata alla dimensione dei BLOB di input.

Problemi correlati