Błąd Caffe Nie można skopiować wartości parametrów 0 z warstwy, niedopasowanie kształtu

Otrzymuję następujący błąd podczas uruchamiania aplikacji testowej. (Gdy używam wyszkolony modelu z mojej aplikacji testowej)Błąd Caffe Nie można skopiować wartości parametrów 0 z warstwy, niedopasowanie kształtu

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)

Może ktoś powiedzieć jakie są tego powody?

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" 
}

Źródło

2016-05-18 Deepak

Udostępniaj plik prototekstu, którego użyto do szkolenia i testowania w celu wskazania problemu. Powinno to być głównie dlatego, że wymiary obrazu wejściowego nie są takie same zarówno w protokole testowym, jak iw prototeksie pociągu. Sprawdź wysokość, szerokość i liczbę kanałów zarówno prototypu testu, jak i pociągu. –

Udało mi się właściwie wyszkolić caffe, dzieje się to w aplikacji testowej, w której używam wyszkolonego modelu caffe. – Deepak

OK, teraz działa po poprawieniu wartości dim przy deploy.txt działa – Deepak

Szkolenie odbywa się na obrazie wymiaru 256x256x3, ale protokół testowy próbuje odczytać obraz 227x227x3. Warstwy splotowe nie będą wykazywały żadnego problemu, ponieważ rozmiar wejściowych obiektów typu blob do warstw splotowych nie ma znaczenia. W pełni połączone warstwy ulegną awarii, gdy stwierdzi, że blob wejściowy ma inny wymiar. Innymi słowy, wymiar ciężaru całkowicie połączonej warstwy jest związany z wymiarem wejściowych obiektów typu blob.

Źródło

2016-05-18 15:39:36

Błąd Caffe Nie można skopiować wartości parametrów 0 z warstwy, niedopasowanie kształtu

Odpowiedz

Powiązane problemy