Caffe - ошибка CNN: RuntimeWarning: деление на ноль, встречающееся в делении - PullRequest
Новая
       19

Caffe - ошибка CNN: RuntimeWarning: деление на ноль, встречающееся в делении

0 голосов
/ 19 мая 2018

Я обучил модель обнаружения лица / эмоций VGG с нуля.Соответствующие файлы и веса объявляются так: 

model_path = 'models/faces/vitor_face/' # substitute your path here
net_fn   = model_path + 'VGG_FACE_deploy.prototxt'
param_fn = model_path + '_iter_3000.caffemodel.h5'

model = caffe.io.caffe_pb2.NetParameter()
text_format.Merge(open(net_fn).read(), model)
model.force_backward = True

net = caffe.Classifier('models/faces/vitor_face/tmp.prototxt', param_fn,
                       mean = np.float32([104.0, 116.0, 122.0]), # ImageNet mean, training set dependent
                       channel_swap = (2,1,0)) # the reference model has channels in BGR order instead of RGB

, затем я пытаюсь использовать эту модель для оптимизации определенного входного изображения и генерирования на нем «снов», выбрав и end слой объектива.,Итак, если у меня есть сеть с такой архитектурой, как:

VGG_FACE_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"
}

temp.prototxt 

name: "VGG_FACE_16_layers"
layers {
  bottom: "data"
  top: "conv1"
  name: "conv1"
  type: CONVOLUTION
  convolution_param {
    num_output: 64
    pad: 1
    kernel_size: 3
  }
}
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
  bottom: "fc8"
  top: "prob"
}
input: "data"
input_dim: 1
input_dim: 3
input_dim: 224
input_dim: 224
force_backward: true

и я объявляю "conv5" своей целью, я использую следующий код, чтобы попытаться сгенерировать мои «мечты»: 

def make_step(net, step_size=1.5, end="conv5", 
              jitter=32, clip=True, objective=objective_L2):
    '''Basic gradient ascent step.'''

    src = net.blobs['data'] # input image is stored in Net's 'data' blob
    dst = net.blobs[end]
    print ('src.data', src.data)

    ox, oy = np.random.randint(-jitter, jitter+1, 2)
    src.data[0] = np.roll(np.roll(src.data[0], ox, -1), oy, -2) # apply jitter shift

    net.forward(end=end)
    objective(dst)  # specify the optimization objective
    net.backward(start=end)
    g = src.diff[0]
    print ('G',g)
    # apply normalized ascent step to the input image
    src.data[:] += step_size/np.abs(g).mean() * g

    src.data[0] = np.roll(np.roll(src.data[0], -ox, -1), -oy, -2) # unshift image

    if clip:
        bias = net.transformer.mean['data']
        src.data[:] = np.clip(src.data, -bias, 255-bias)


def deepdream(net, base_img, iter_n=20, octave_n=4, octave_scale=1.4, 
              end="conv5", clip=True, **step_params):

    # prepare base images for all octaves
    octaves = [preprocess(net, base_img)]

    for i in xrange(octave_n-1):
        octaves.append(nd.zoom(octaves[-1], (1, 1.0/octave_scale,1.0/octave_scale), order=1))

    src = net.blobs['data']
    #print src.data
    # print blobs infos
    print [(k, v.data.shape) for k, v in net.blobs.items()]
    #print weight and bias parameters
    print [(k, v[0].data.shape, v[1].data.shape) for k, v in net.params.items()]

    detail = np.zeros_like(octaves[-1]) # allocate image for network-produced details

    for octave, octave_base in enumerate(octaves[::-1]):
        h, w = octave_base.shape[-2:]

        if octave > 0:
            # upscale details from the previous octave
            h1, w1 = detail.shape[-2:]
            detail = nd.zoom(detail, (1, 1.0*h/h1,1.0*w/w1), order=1)

        src.reshape(1,3,h,w) # resize the network's input image size
        src.data[0] = octave_base+detail

        for i in xrange(20):
            make_step(net, end=end, clip=clip, **step_params)

            # visualization
            vis = deprocess(net, src.data[0])

            if not clip: # adjust image contrast if clipping is disabled
                vis = vis*(255.0/np.percentile(vis, 99.98))
            showarray(vis)
            # save images to disk
            PIL.Image.fromarray(np.uint8(vis)).save('results/{}_{}_{}.png'.format(octave, i, vis.shape))

            print octave, i, end, vis.shape
            clear_output(wait=True)

        # extract details produced on the current octave
        detail = src.data[0]-octave_base
    # returning the resulting image
    return deprocess(net, src.data[0])

но когда я запускаю этот процесс, я получаю следующую ошибку: 

dream.py:145: RuntimeWarning: divide by zero encountered in divide
  src.data[:] += step_size/np.abs(g).mean() * g
dream.py:145: RuntimeWarning: invalid value encountered in multiply
  src.data[:] += step_size/np.abs(g).mean() * g

src.data печатает: 

<IPython.core.display.Image object>
0 0 conv5 (193, 342, 3)
('src.data', array([[[[ nan,  nan,  nan, ...,  nan,  nan,  nan],
         [ nan,  nan,  nan, ...,  nan,  nan,  nan],
         [ nan,  nan,  nan, ...,  nan,  nan,  nan],
         ..., 
         [ nan,  nan,  nan, ...,  nan,  nan,  nan],
         [ nan,  nan,  nan, ...,  nan,  nan,  nan],
         [ nan,  nan,  nan, ...,  nan,  nan,  nan]],

        [[ nan,  nan,  nan, ...,  nan,  nan,  nan],
         [ nan,  nan,  nan, ...,  nan,  nan,  nan],
         [ nan,  nan,  nan, ...,  nan,  nan,  nan],
         ..., 
         [ nan,  nan,  nan, ...,  nan,  nan,  nan],
         [ nan,  nan,  nan, ...,  nan,  nan,  nan],
         [ nan,  nan,  nan, ...,  nan,  nan,  nan]],

        [[ nan,  nan,  nan, ...,  nan,  nan,  nan],
         [ nan,  nan,  nan, ...,  nan,  nan,  nan],
         [ nan,  nan,  nan, ...,  nan,  nan,  nan],
         ..., 
         [ nan,  nan,  nan, ...,  nan,  nan,  nan],
         [ nan,  nan,  nan, ...,  nan,  nan,  nan],
         [ nan,  nan,  nan, ...,  nan,  nan,  nan]]]], dtype=float32))

если я исправлю эту строку: 

src.data[:] += step_size/np.abs(g).mean() * g

добавив к ней 'смещение', например g+.1, код не нарушается и генерирует значения, отличные от 0, но изображения снов тоже не генерируются.

что не так с моей моделью?любая помощь будет высоко ценится.

Добро пожаловать на сайт PullRequest, где вы можете задавать вопросы и получать ответы от других членов сообщества.

Похожие темы

...