075c34d037ec564aa9c923a653c2cc3135c99510,keras/backend/tensorflow_backend.py,,pool2d,#Any#Any#Any#Any#Any#Any#,548

Before Change

        // tf max_pool only supports float32
        x = tf.cast(x, "float32")

    if dim_ordering == "th":
        // TF uses the last dimension as channel dimension,
        // instead of the 2nd one.
        // TH input shape: (samples, input_depth, rows, cols)
        // TF input shape: (samples, rows, cols, input_depth)
        // TH kernel shape: (depth, input_depth, rows, cols)
        // TF kernel shape: (rows, cols, input_depth, depth)
        x = tf.transpose(x, (0, 2, 3, 1))
        if pool_mode=="max":
            x = tf.nn.max_pool(x, pool_size, strides, padding=padding)
        elif pool_mode=="mean":
            x = tf.nn.avg_pool(x, pool_size, strides, padding=padding)
        else:
            raise Exception("Invalid pooling mode: " + str(pool_mode))
        x = tf.transpose(x, (0, 3, 1, 2))
    elif dim_ordering == "tf":
        if pool_mode=="max":
            x = tf.nn.max_pool(x, pool_size, strides, padding=padding)
        elif pool_mode=="mean":
            x = tf.nn.avg_pool(x, pool_size, strides, padding=padding)
        else:
            raise Exception("Invalid pooling mode: " + str(pool_mode))
    else:
        raise Exception("Unknown dim_ordering: " + str(dim_ordering))

    if _FLOATX == "float64":
        x = tf.cast(x, "float64")
    return x

After Change

        // tf max_pool only supports float32
        x = tf.cast(x, "float32")

    if dim_ordering in {"tf", "th"}:
        if dim_ordering == "th":
            // TF uses the last dimension as channel dimension,
            // instead of the 2nd one.
            // TH input shape: (samples, input_depth, rows, cols)
            // TF input shape: (samples, rows, cols, input_depth)
            // TH kernel shape: (depth, input_depth, rows, cols)
            // TF kernel shape: (rows, cols, input_depth, depth)
            x = tf.transpose(x, (0, 2, 3, 1))
        if pool_mode == "max":
            x = tf.nn.max_pool(x, pool_size, strides, padding=padding)
        elif pool_mode == "avg":
            x = tf.nn.avg_pool(x, pool_size, strides, padding=padding)
        else:
            raise Exception("Invalid pooling mode: " + str(pool_mode))
        if dim_ordering == "th":
            x = tf.transpose(x, (0, 3, 1, 2))
    else:
        raise Exception("Unknown dim_ordering: " + str(dim_ordering))

    if _FLOATX == "float64":

Instances