ONNX和pytorch之间的输出不同

我尝试将我的pytorch Resnet50模型转换为ONNX并进行推理。转换过程没有错误，但的onnx模型的最终结果与Pyrotch的原始模型的结果存在较大差距
什么是可能的解决方案？

ONNX的版本：1.5.0
pytorch的版本：1.1.0
CUDA:9.0
系统：Ubuntu 18.06
Python:3.5

这是转换代码

导入火炬
导入模型
从集合导入订单
state_dict=“/home/yx wan/newhome/workspace/filter prunning几何中值/脚本/快照/resnet50-rate-0.7/best.resnet50.GM_0.7_76.82.pth.tar”
arch='resnet50'
def导入稀疏（模型、状态）：
new_state_dict=OrderedDict（）
对于处于状态的k，v_dict.items（）：
name=k[7:]#删除`模块`
新状态记录[名称]=v
模型。加载状态记录（新状态记录）
打印（“稀疏模型加载”）
回归模型
#初始化模型
model=models.\uuuu dict\uuuuu[arch]（pretrained=False）.cuda（）
检查点=火炬荷载（状态）
模型=导入稀疏（模型，检查点['state\u dict']）
打印（“模型的前1名：{}”。格式（检查点['best_prec1']））
dummy_input=torch.randn（1,3,224,224）.cuda（）
导出（模型，伪输入，“{}.onnx.”格式（arch），verbose=True）

这是结果检查代码

导入系统 从onnxruntime.datasets导入get\u示例 导入onnxruntime 进口cv2 将numpy作为np导入 进口火炬 导入模型 导入onnxruntime 从集合导入订单 从“我的工具”导入调整大小\u img def导入_稀疏（模型、检查点）： new_state_dict=OrderedDict（） 对于检查点['state_dict']中的k，v。items（）： name=k[7:]#删除`模块` 新状态记录[名称]=v 模型。加载状态记录（新状态记录） 回归模型 image_path=“/img652.jpg” onnx_model_path=“/workplace/workspace/filter prunning几何中值/resnet50.onnx” ckpt=“./scripts/snapshots/resnet50-rate-0.7/best.resnet50.GM_0.7_76.82.pth.tar” img_ori=cv2.imread（图像路径）#BGR img=cv2.cvt颜色（img_ori，cv2.COLOR_BGR2RGB） img，ratio\u h，ratio\u w=调整大小\u img（img，224） img=img-np.array（[123.68116.78103.94]，dtype=np.float32） img\u batch=np.展开尺寸（img，0） #NHWC->NCHW img_batch=np.转置（img_batch[0,3,1,2]） 示例\u模型=获取\u示例（onnx\u模型\u路径） sess=onnxruntime.推断会话（示例\模型） input_name=sess.get_inputs（）[0].name 打印（“输入名称：”，输入名称） input_shape=sess.get_inputs（）[0]。shape 打印（“输入形状：”，输入形状） input_type=sess.get_inputs（）[0]。键入 打印（“输入类型：”，输入类型） output\u name=sess.get\u outputs（）[0].name 打印（“输出名称：”，输出名称） output\u shape=sess.get\u outputs（）[0]。shape 打印（“输出形状：”，输出形状） output\u type=sess.get\u outputs（）[0]。键入 打印（“输出类型：”，输出类型） 打印（“输入数据形状{}”.format（img_batch.shape）） 断言（list（input_shape）==list（img_batch.shape）） result_onnx=sess.run（[output_name]，{input_name:img_batch}） #初始化模型 model=models.uuuu dict_uuuuu[“resnet50”]（） checkpoint=torch.load（ckpt，map\u location='cpu'） best_prec1=检查点['best_prec1'] 模型=导入\u稀疏（模型，检查点） img\U批次=火炬浮动张量（img\U批次） 使用手电筒。无梯度（） 结果\u火炬=模型（img\u批次） result\u torch=result\u torch.numpy（） 打印（“max onnx torch:{}”。格式（np.max（result\u onnx-result\u torch））） 检查代码的输出（带有一些警告，但我认为这无关紧要）是

2019-08-09 02:59:21.378599853 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer4.2.bn3.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.378654931 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer4.2.bn2.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.378665235 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer4.2.bn1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.378675069 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer4.1.bn3.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.378686874 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer4.0.downsample.1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.378698995 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer4.1.bn1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.378718700 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer3.5.bn1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.378729567 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer3.4.bn3.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.378739657 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer3.4.bn2.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.378752091 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer3.3.bn3.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.378762533 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer3.3.bn1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.378771168 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer3.2.bn3.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.378781705 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer3.2.bn1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.378792325 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer3.4.bn1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.378802071 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer3.1.bn3.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.378812061 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer4.0.bn3.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.378822884 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer3.1.bn2.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.378834198 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer3.0.downsample.1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.378845176 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer1.2.bn1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.378859324 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer2.0.bn1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.378869709 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer2.0.bn2.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.378883281 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer3.5.bn3.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.378893302 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer2.3.bn1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.378904876 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer1.1.bn2.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.378915507 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer1.0.bn3.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.378926638 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer4.0.bn2.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.378938115 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer3.0.bn1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.378948686 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'bn1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.378958670 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer3.2.bn2.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.378969125 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer4.1.bn2.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.378979556 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer2.1.bn1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.378990553 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer2.2.bn1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.379001126 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer1.2.bn2.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.379011508 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer1.0.bn2.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.379021900 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer1.0.downsample.1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.379033504 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer2.2.bn3.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.379044076 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer1.2.bn3.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.379064049 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer1.1.bn1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.379076654 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer2.0.bn3.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.379089769 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer2.1.bn2.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.379102140 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer3.0.bn2.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.379114598 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer3.3.bn2.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.379133520 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer2.2.bn2.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.379144015 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer2.3.bn2.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.379155771 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer1.1.bn3.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.379167084 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer2.3.bn3.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.379178303 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer3.0.bn3.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.379189605 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer4.0.bn1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.379199974 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer3.1.bn1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.379211042 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer2.0.downsample.1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.379221800 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer3.5.bn2.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.379232566 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer1.0.bn1.num_batches_tracked'. It is not used by any node and should be removed from the model.
2019-08-09 02:59:21.379243442 [W:onnxruntime:Default, graph.cc:2263 CleanUnusedInitializers] Removing initializer 'layer2.1.bn3.num_batches_tracked'. It is not used by any node and should be removed from the model.
Input name  : 0
Input shape : [1, 3, 224, 224]
Input type  : tensor(float)
Output name  : 503
Output shape : [1, 1000]
Output type  : tensor(float)
Input data shape(1, 3, 224, 224)
max onnx-torch:104.89282989501953

---

在测试代码中运行pytorch模型推断之前，通过添加model.eval（）来解决问题。解决办法是

---

只是想提供一些额外的细节。当您将模型置于

eval

模式时，某些层的行为将不同（例如，退出和批处理）。在您的案例中，输出的差异是因为batchnorm在（默认）

train

模式下使用批次统计信息，在

eval

模式下使用历史统计信息。

model = models.__dict__["resnet50"]()
checkpoint = torch.load(ckpt,map_location='cpu')
best_prec1 = checkpoint['best_prec1']
model = import_sparse(model,checkpoint)
model.eval()
img_batch = torch.FloatTensor(img_batch)
with torch.no_grad():
    result_torch = model(img_batch)
    result_torch = result_torch.numpy()