我已将 Tensorflow 模型转换为 Tensorflow JS 并尝试在浏览器中使用。在将输入输出输入模型进行推理之前,需要在输入输出上执行一些预处理步骤。我已经实现了与 Tensorflow 相同的这些步骤。问题是 TF JS 的推理结果与 Tensorflow 不同。所以我开始调试代码,发现TF JS预处理中浮点算术运算的结果与运行在带有GPU的Docker容器上的Tensorflow不同。TF JS 中使用的代码如下。
var tensor3d = tf.tensor3d(image,[height,width,1],'float32')
var pi= PI.toString();
if(bs == 14 && pi.indexOf('1') != -1 ) {
tensor3d = tensor3d.sub(-9798.6993999999995).div(7104.607118190255)
}
else if(bs == 12 && pi.indexOf('1') != -1) {
tensor3d = tensor3d.sub(-3384.9893000000002).div(1190.0708513300835)
}
else if(bs == 12 && pi.indexOf('2') != -1) {
tensor3d = tensor3d.sub(978.31200000000001).div(1092.2426342420442)
}
var resizedTensor = tensor3d.resizeNearestNeighbor([224,224]).toFloat()
var copiedTens = tf.tile(resizedTensor,[1,1,3])
return copiedTens.expandDims();
使用的 Python 代码块
ds = pydicom.dcmread(input_filename, stop_before_pixels=True)
if (ds.BitsStored == 12) and '1' in ds.PhotometricInterpretation:
normalize_mean = -3384.9893000000002
normalize_std = 1190.0708513300835
elif (ds.BitsStored == 12) and '2' in ds.PhotometricInterpretation:
normalize_mean = 978.31200000000001
normalize_std = 1092.2426342420442
elif (ds.BitsStored == 14) and '1' in ds.PhotometricInterpretation:
normalize_mean = -9798.6993999999995
normalize_std = 7104.607118190255
else:
error_response = "Unable to read required metadata, or metadata invalid.
BitsStored: {}. PhotometricInterpretation: {}".format(ds.BitsStored,
ds.PhotometricInterpretation)
error_json = {'code': 500, 'message': error_response}
self._set_headers(500)
self.wfile.write(json.dumps(error_json).encode())
return
normalization = Normalization(mean=normalize_mean, std=normalize_std)
resize = ResizeImage()
copy_channels = CopyChannels()
inference_data_collection.append_preprocessor([normalization, resize,
copy_channels])
规范化代码
def normalize(self, normalize_numpy, mask_numpy=None):
normalize_numpy = normalize_numpy.astype(float)
if mask_numpy is not None:
mask = mask_numpy > 0
elif self.mask_zeros:
mask = np.nonzero(normalize_numpy)
else:
mask = None
if mask is None:
normalize_numpy = (normalize_numpy - self.mean) / self.std
else:
raise NotImplementedError
return normalize_numpy
调整大小图像代码
from skimage.transform import resize
def Resize(self, data_group):
input_data = data_group.preprocessed_case
output_data = resize(input_data, self.output_dim)
data_group.preprocessed_case = output_data
self.output_data = output_data
CopyChannels 代码
def CopyChannels(self, data_group):
input_data = data_group.preprocessed_case
if self.new_channel_dim:
output_data = np.stack([input_data] * self.channel_multiplier, -1)
else:
output_data = np.tile(input_data, (1, 1, self.channel_multiplier))
data_group.preprocessed_case = output_data
self.output_data = output_data
示例输出左侧是带有 GPU 的 Docker 上的 Tensorflow,右侧是 TF JS:
每一步之后的结果实际上是不同的。