Function ResNet50

tensorlayer/models/resnet.py:114–176

Pre-trained MobileNetV1 model (static mode). Input shape [?, 224, 224, 3]. To use pretrained model, input should be in BGR format and subtracted from ImageNet mean [103.939, 116.779, 123.68]. Parameters ---------- pretrained : boolean Whether to load pretrained weights. Defa

(pretrained=False, end_with='fc1000', n_classes=1000, name=None)

def ResNet50(pretrained=False, end_with='fc1000', n_classes=1000, name=None):
    """Pre-trained MobileNetV1 model (static mode). Input shape [?, 224, 224, 3].
    To use pretrained model, input should be in BGR format and subtracted from ImageNet mean [103.939, 116.779, 123.68].

    Parameters
    ----------
    pretrained : boolean
        Whether to load pretrained weights. Default False.
    end_with : str
        The end point of the model [conv, depth1, depth2 ... depth13, globalmeanpool, out].
        Default ``out`` i.e. the whole model.
    n_classes : int
        Number of classes in final prediction.
    name : None or str
        Name for this model.

    Examples
    ---------
    Classify ImageNet classes, see `tutorial_models_resnet50.py`

    >>> # get the whole model with pretrained weights
    >>> resnet = tl.models.ResNet50(pretrained=True)
    >>> # use for inferencing
    >>> output = resnet(img1, is_train=False)
    >>> prob = tf.nn.softmax(output)[0].numpy()

    Extract the features before fc layer
    >>> resnet = tl.models.ResNet50(pretrained=True, end_with='5c')
    >>> output = resnet(img1, is_train=False)

    Returns
    -------
        ResNet50 model.

    """
    ni = Input([None, 224, 224, 3], name="input")
    n = Conv2d(64, (7, 7), strides=(2, 2), padding='SAME', W_init=tf.initializers.he_normal(), name='conv1')(ni)
    n = BatchNorm(name='bn_conv1', act='relu')(n)
    n = MaxPool2d((3, 3), strides=(2, 2), name='max_pool1')(n)

    for i, block_name in enumerate(block_names):
        if len(block_name) == 2:
            stage = int(block_name[0])
            block = block_name[1]
            if block == 'a':
                strides = (1, 1) if stage == 2 else (2, 2)
                n = conv_block(n, 3, block_filters[stage - 2], stage=stage, block=block, strides=strides)
            else:
                n = identity_block(n, 3, block_filters[stage - 2], stage=stage, block=block)
        elif block_name == 'avg_pool':
            n = GlobalMeanPool2d(name='avg_pool')(n)
        elif block_name == 'fc1000':
            n = Dense(n_classes, name='fc1000')(n)

        if block_name == end_with:
            break

    network = Model(inputs=ni, outputs=n, name=name)