Python inference_time_wise_filter Examples

Example #1

File: autorun_infer_pooling_1layer.py Project: AliMiraftab/ROICNN

def inference_global_s_cnn_1layer(images, keep_prob, feat=[4]):

    _print_tensor_size(images, 'inference_global_s_cnn')
    assert isinstance(keep_prob, object)
    # here use the spatial filter which go across time
    conv_tensor = rsvp_quick_inference.inference_time_wise_filter(images, 'conv1', out_feat=feat[0])
    pool_tensor = rsvp_quick_inference.inference_pooling_n_filter(conv_tensor, kheight=1)
    logits = rsvp_quick_inference.inference_fully_connected_1layer(pool_tensor, keep_prob)

    assert isinstance(logits, object)
    return logits

Example #2

File: autorun_infer_no_pooling_1layer.py Project: jingxiachen/ROICNN

def inference_global_s_cnn_1layer(images, keep_prob, feat=[4]):

    _print_tensor_size(images, 'inference_global_s_cnn')
    assert isinstance(keep_prob, object)
    # here use the spatial filter which go across time
    conv_tensor = rsvp_quick_inference.inference_time_wise_filter(
        images, 'conv1', out_feat=feat[0])

    logits = rsvp_quick_inference.inference_fully_connected_1layer(
        conv_tensor, keep_prob)

    assert isinstance(logits, object)
    return logits

Example #3

File: autorun_infer.py Project: ZijingMao/ROICNN

def inference_global_s_cnn(images, keep_prob, layer=1, feat=[4]):

    _print_tensor_size(images, 'inference_global_s_cnn')
    assert isinstance(keep_prob, object)

    # global s
    # here use the spatial filter which go across time
    conv_tensor = rsvp_quick_inference.inference_time_wise_filter(images, 'conv1', out_feat=feat[0])
    # the pooling should have the height padding to 1 because no channel anymore
    pool_tensor = rsvp_quick_inference.inference_pooling_n_filter(conv_tensor, kheight=1)

    logits = rsvp_quick_inference.inference_fully_connected_1layer(pool_tensor, keep_prob)

    assert isinstance(logits, object)
    return logits

Example #4

File: autorun_infer.py Project: AliMiraftab/ROICNN

def inference_global_s_cnn(images, keep_prob, layer=1, feat=[4]):

    _print_tensor_size(images, 'inference_global_s_cnn')
    assert isinstance(keep_prob, object)

    # global s
    # here use the spatial filter which go across time
    conv_tensor = rsvp_quick_inference.inference_time_wise_filter(images, 'conv1', out_feat=feat[0])
    # the pooling should have the height padding to 1 because no channel anymore
    pool_tensor = rsvp_quick_inference.inference_pooling_n_filter(conv_tensor, kheight=1)

    logits = rsvp_quick_inference.inference_fully_connected_1layer(pool_tensor, keep_prob)

    assert isinstance(logits, object)
    return logits