Question

Я обучил модель CNN VGG_face caffe с нуля и сохранил обучающие снимки в формате HDF5, и, очевидно, обучение до итерации 3000 не имело проблем.

solver.prototxt

net: "models/Custom_Model/train.prototxt"
# test_iter specifies how many forward passes the test should carry out
test_iter: 1
# Carry out testing every X training iterations
test_interval: 20
# Learning rate and momentum parameters for Adam
base_lr: 0.001
momentum: 0.9
momentum2: 0.999
# Adam takes care of changing the learning rate
lr_policy: "fixed"
# Display every X iterations
display: 10
# The maximum number of iterations
max_iter: 3000
# snapshot intermediate results
snapshot: 100
snapshot_prefix: "snapshots/"
snapshot_format: HDF5
# solver mode: CPU or GPU
type: "Adam"
solver_mode: CPU

Однако что-то пошло не так, потому что, когда я пытаюсь загрузить сеть для проверки на классификацию, например:

net = caffe.Net('models/my_face/deploy.prototxt', 'models/my_face/_iter_3000.solverstate.h5', caffe.TEST)
net.save('models/my_face/my_face.caffemodel')

Я получаю следующую ошибку:

HDF5-DIAG: Error detected in HDF5 (1.8.11) thread 139907437496128:
  #000: ../../../src/H5G.c line 463 in H5Gopen2(): unable to open group
    major: Symbol table
    minor: Can't open object
  #001: ../../../src/H5Gint.c line 320 in H5G__open_name(): group not found
    major: Symbol table
    minor: Object not found
  #002: ../../../src/H5Gloc.c line 430 in H5G_loc_find(): can't find object
    major: Symbol table
    minor: Object not found
  #003: ../../../src/H5Gtraverse.c line 861 in H5G_traverse(): internal path traversal failed
    major: Symbol table
    minor: Object not found
  #004: ../../../src/H5Gtraverse.c line 641 in H5G_traverse_real(): traversal operator failed
    major: Symbol table
    minor: Callback failed
  #005: ../../../src/H5Gloc.c line 385 in H5G_loc_find_cb(): object 'data' doesn't exist
    major: Symbol table
    minor: Object not found
F0608 18:00:59.386113   154 net.cpp:802] Check failed: data_hid >= 0 (-1 vs. 0) Error reading weights from models/vitor_face/_iter_3000.solverstate.h5
*** Check failure stack trace: ***
Aborted

deploy.prototxt

name: "VGG_FACE_16_layers"
input: "data"
input_dim: 1
input_dim: 3
input_dim: 224
input_dim: 224
layers {
  name: "conv1"
  type: CONVOLUTION
  bottom: "data"
  top: "conv1"
  convolution_param {
    num_output: 96
    kernel_size: 7
    stride: 2
  }
}
layers {
  name: "relu1"
  type: RELU
  bottom: "conv1"
  top: "conv1"
}
layers {
  name: "norm1"
  type: LRN
  bottom: "conv1"
  top: "norm1"
  lrn_param {
    local_size: 5
    alpha: 0.0005
    beta: 0.75
  }
}
layers {
  name: "pool1"
  type: POOLING
  bottom: "norm1"
  top: "pool1"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 3
  }
}
layers {
  name: "conv2"
  type: CONVOLUTION
  bottom: "pool1"
  top: "conv2"
  convolution_param {
    num_output: 256
    pad: 2
    kernel_size: 5
  }
}
layers {
  name: "relu2"
  type: RELU
  bottom: "conv2"
  top: "conv2"
}
layers {
  name: "pool2"
  type: POOLING
  bottom: "conv2"
  top: "pool2"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layers {
  name: "conv3"
  type: CONVOLUTION
  bottom: "pool2"
  top: "conv3"
  convolution_param {
    num_output: 512
    pad: 1
    kernel_size: 3
  }
}
layers {
  name: "relu3"
  type: RELU
  bottom: "conv3"
  top: "conv3"
}
layers {
  name: "conv4"
  type: CONVOLUTION
  bottom: "conv3"
  top: "conv4"
  convolution_param {
    num_output: 512
    pad: 1
    kernel_size: 3
  }
}
layers {
  name: "relu4"
  type: RELU
  bottom: "conv4"
  top: "conv4"
}
layers {
  name: "conv5"
  type: CONVOLUTION
  bottom: "conv4"
  top: "conv5"
  convolution_param {
    num_output: 512
    pad: 1
    kernel_size: 3
  }
}
layers {
  name: "relu5"
  type: RELU
  bottom: "conv5"
  top: "conv5"
}
layers {
  name: "pool5"
  type: POOLING
  bottom: "conv5"
  top: "pool5"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 3
  }
}
layers {
  name: "fc6"
  type: INNER_PRODUCT
  bottom: "pool5"
  top: "fc6"
  inner_product_param {
    num_output: 4048
  }
}
layers {
  name: "relu6"
  type: RELU
  bottom: "fc6"
  top: "fc6"
}
layers {
  name: "drop6"
  type: DROPOUT
  bottom: "fc6"
  top: "fc6"
  dropout_param {
    dropout_ratio: 0.5
  }
}
layers {
  name: "fc7"
  type: INNER_PRODUCT
  bottom: "fc6"
  top: "fc7"
  inner_product_param {
    num_output: 4048
  }
}
layers {
  name: "relu7"
  type: RELU
  bottom: "fc7"
  top: "fc7"
}
layers {
  name: "drop7"
  type: DROPOUT
  bottom: "fc7"
  top: "fc7"
  dropout_param {
    dropout_ratio: 0.5
  }
}
layers {
  name: "fc8_cat"
  type: INNER_PRODUCT
  bottom: "fc7"
  top: "fc8"
  inner_product_param {
    num_output: 6
  }
}
layers {
  name: "prob"
  type: SOFTMAX
  bottom: "fc8"
  top: "prob"
}

Я вмешался с некоторыми net_surgery в порядкечтобы отладить это, и вот что печатает моя архитектура:

blobs ['data', 'conv1', 'norm1', 'pool1', 'conv2', 'pool2', 'conv3', 'conv4', 'conv5', 'pool5', 'fc6', 'fc7', 'fc8', 'prob']
params ['conv1', 'conv2', 'conv3', 'conv4', 'conv5', 'fc6', 'fc7', 'fc8_cat']
('POOL 5', (512, 7, 7))
  Layer Name :   conv1, Weight Dims :(96, 3, 7, 7) 
  Layer Name :   conv2, Weight Dims :(256, 96, 5, 5) 
  Layer Name :   conv3, Weight Dims :(512, 256, 3, 3) 
  Layer Name :   conv4, Weight Dims :(512, 512, 3, 3) 
  Layer Name :   conv5, Weight Dims :(512, 512, 3, 3) 
  Layer Name :     fc6, Weight Dims :(4048, 25088) 
  Layer Name :     fc7, Weight Dims :(4048, 4048) 
  Layer Name : fc8_cat, Weight Dims :(6, 4048)    
fc6 weights are (4048, 25088) dimensional and biases are (4048,) dimensional
fc7 weights are (4048, 4048) dimensional and biases are (4048,) dimensional
fc8_cat weights are (6, 4048) dimensional and biases are (6,) dimensional

train.prototxt

name: "CaffeNet"
layers {
  name: "training_train"
  type: DATA
  data_param {
    source: "datasets/training_set_lmdb"
    backend: LMDB
    batch_size: 10
  }
  transform_param{
    mean_file: "datasets/mean_training_image.binaryproto"
  }
  top: "data"
  top: "label"
  include {
    phase: TRAIN
  }
}
layers {
  name: "training_test"
  type: DATA
  data_param {
    source: "datasets/validation_set_lmdb"
    backend: LMDB
    batch_size: 1
  }
  transform_param{
    mean_file: "datasets/mean_training_image.binaryproto"
  }
  top: "data"
  top: "label"
  include {
    phase: TEST
  }
}
layers {
  name: "conv1"
  type: CONVOLUTION
  bottom: "data"
  top: "conv1"
  convolution_param {
    num_output: 96
    kernel_size: 7
    stride: 2
  }
  blobs_lr: 0
  blobs_lr: 0
}
layers {
  name: "relu1"
  type: RELU
  bottom: "conv1"
  top: "conv1"
}
layers {
  name: "norm1"
  type: LRN
  bottom: "conv1"
  top: "norm1"
  lrn_param {
    local_size: 5
    alpha: 0.0005
    beta: 0.75
  }
}
layers {
  name: "pool1"
  type: POOLING
  bottom: "norm1"
  top: "pool1"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 3
  }
}
layers {
  name: "conv2"
  type: CONVOLUTION
  bottom: "pool1"
  top: "conv2"
  convolution_param {
    num_output: 256
    pad: 2
    kernel_size: 5
  }
  blobs_lr: 0
  blobs_lr: 0
}
layers {
  name: "relu2"
  type: RELU
  bottom: "conv2"
  top: "conv2"
}
layers {
  name: "pool2"
  type: POOLING
  bottom: "conv2"
  top: "pool2"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layers {
  name: "conv3"
  type: CONVOLUTION
  bottom: "pool2"
  top: "conv3"
  convolution_param {
    num_output: 512
    pad: 1
    kernel_size: 3
  }
  blobs_lr: 0
  blobs_lr: 0
}
layers {
  name: "relu3"
  type: RELU
  bottom: "conv3"
  top: "conv3"
}
layers {
  name: "conv4"
  type: CONVOLUTION
  bottom: "conv3"
  top: "conv4"
  convolution_param {
    num_output: 512
    pad: 1
    kernel_size: 3
  }
  blobs_lr: 0
  blobs_lr: 0
}
layers {
  name: "relu4"
  type: RELU
  bottom: "conv4"
  top: "conv4"
}
layers {
  name: "conv5"
  type: CONVOLUTION
  bottom: "conv4"
  top: "conv5"
  convolution_param {
    num_output: 512
    pad: 1
    kernel_size: 3
  }
  blobs_lr: 0
  blobs_lr: 0
}
layers {
  name: "relu5"
  type: RELU
  bottom: "conv5"
  top: "conv5"
}
layers {
  name: "pool5"
  type: POOLING
  bottom: "conv5"
  top: "pool5"
  pooling_param {
    pool: MAX
    kernel_size: 3
    stride: 3
  }
}
layers {
  name: "fc6"
  type: INNER_PRODUCT
  bottom: "pool5"
  top: "fc6"
  inner_product_param {
    num_output: 4048
  }
  blobs_lr: 1.0
  blobs_lr: 1.0
}
layers {
  name: "relu6"
  type: RELU
  bottom: "fc6"
  top: "fc6"
}
layers {
  name: "drop6"
  type: DROPOUT
  bottom: "fc6"
  top: "fc6"
  dropout_param {
    dropout_ratio: 0.5
  }
}
layers {
  name: "fc7"
  type: INNER_PRODUCT
  bottom: "fc6"
  top: "fc7"
  inner_product_param {
    num_output: 4048
  }
  blobs_lr: 1.0
  blobs_lr: 1.0
}
layers {
  name: "relu7"
  type: RELU
  bottom: "fc7"
  top: "fc7"
}
layers {
  name: "drop7"
  type: DROPOUT
  bottom: "fc7"
  top: "fc7"
  dropout_param {
    dropout_ratio: 0.5
  }
}
layers {
  name: "fc8_cat"
  type: INNER_PRODUCT
  bottom: "fc7"
  top: "fc8"
  inner_product_param {
    num_output: 6
  }
  blobs_lr: 1.0
  blobs_lr: 1.0
}
layers {
  name: "prob"
  type: SOFTMAX_LOSS
  bottom: "fc8"
  bottom: "label"
}

как мне исправить эту проблему?

Caffe - невозможно загрузить модель HDF5

Пожалуйста, войдите или зарегистрируйтесь чтобы ответить на этот вопрос.

Ответы [ 0 ]

Caffe - невозможно загрузить модель HDF5

Пожалуйста, войдите или зарегистрируйтесь чтобы ответить на этот вопрос.

Ответы [ 0 ]

Похожие темы