Working
I'm working on sagemaker jupyter notebook (environement: anaconda3/envs/mxnet_p36/lib/python3.6).
I run successfully this tutorial: https://github.com/onnx/tutorials/blob/master/tutorials/MXNetONNXExport.ipynb
Not working
Then, on the same evironement, I tried to apply the same process to files generated by a sagemaker training job. So, I used as input the S3 model artifact files, changing some lines of the tutorial code to meet my needs. I used built in object detection SSD VGG-16 network with hyperparameter image_shape: 300.
sym = './model_algo_1-symbol.json'
params = './model_algo_1-0000.params'
input_shape = (1,3,300,300)
And verbose=True as last parameter in export_model() method:
converted_model_path = onnx_mxnet.export_model(sym, params, [input_shape], np.float32, onnx_file, True)
When I run the code I got this error (verbose output at the end of the post):
MXNetError: Error in operator multibox_target: [14:36:32] src/operator/contrib/./multibox_target-inl.h:224: Check failed: lshape.ndim() == 3 (-1 vs. 3) : Label should be [batch, num_labels, label_width] tensor
Question
I was not able to find any solution so far:
- maybe the
input_shape = (1,3,300,300)is wrong, but I'm not able to find it out; - maybe the model contains some unexpected layer or so;
Does anybody knows a way to fix this problem or a workaround to use the model on a local machine?
(I mean without having to deploy to aws)
The verbose output:
infer_shape error. Arguments:
data: (1, 3, 300, 300)
conv3_2_weight: (256, 256, 3, 3)
fc7_bias: (1024,)
multi_feat_3_conv_1x1_conv_weight: (128, 512, 1, 1)
conv4_1_bias: (512,)
conv5_3_bias: (512,)
relu4_3_cls_pred_conv_bias: (16,)
multi_feat_2_conv_3x3_relu_cls_pred_conv_weight: (24, 512, 3, 3)
relu4_3_loc_pred_conv_bias: (16,)
relu7_cls_pred_conv_weight: (24, 1024, 3, 3)
conv3_3_bias: (256,)
multi_feat_5_conv_3x3_relu_cls_pred_conv_weight: (16, 256, 3, 3)
conv4_3_weight: (512, 512, 3, 3)
conv1_2_bias: (64,)
multi_feat_2_conv_3x3_relu_cls_pred_conv_bias: (24,)
multi_feat_4_conv_3x3_conv_weight: (256, 128, 3, 3)
conv4_1_weight: (512, 256, 3, 3)
relu4_3_scale: (1, 512, 1, 1)
multi_feat_4_conv_3x3_conv_bias: (256,)
multi_feat_5_conv_3x3_relu_cls_pred_conv_bias: (16,)
conv2_2_weight: (128, 128, 3, 3)
multi_feat_3_conv_3x3_relu_loc_pred_conv_weight: (24, 256, 3, 3)
multi_feat_5_conv_3x3_conv_bias: (256,)
conv5_1_bias: (512,)
multi_feat_3_conv_3x3_conv_bias: (256,)
conv2_1_bias: (128,)
conv5_2_weight: (512, 512, 3, 3)
multi_feat_5_conv_3x3_relu_loc_pred_conv_weight: (16, 256, 3, 3)
multi_feat_4_conv_3x3_relu_loc_pred_conv_weight: (16, 256, 3, 3)
multi_feat_2_conv_3x3_conv_weight: (512, 256, 3, 3)
multi_feat_2_conv_1x1_conv_bias: (256,)
multi_feat_2_conv_1x1_conv_weight: (256, 1024, 1, 1)
conv4_3_bias: (512,)
relu7_cls_pred_conv_bias: (24,)
fc6_bias: (1024,)
conv2_1_weight: (128, 64, 3, 3)
multi_feat_2_conv_3x3_conv_bias: (512,)
multi_feat_2_conv_3x3_relu_loc_pred_conv_weight: (24, 512, 3, 3)
multi_feat_5_conv_1x1_conv_bias: (128,)
relu7_loc_pred_conv_bias: (24,)
multi_feat_3_conv_3x3_relu_loc_pred_conv_bias: (24,)
conv3_3_weight: (256, 256, 3, 3)
conv1_2_weight: (64, 64, 3, 3)
multi_feat_2_conv_3x3_relu_loc_pred_conv_bias: (24,)
conv1_1_bias: (64,)
multi_feat_4_conv_3x3_relu_cls_pred_conv_bias: (16,)
conv4_2_weight: (512, 512, 3, 3)
conv5_3_weight: (512, 512, 3, 3)
relu7_loc_pred_conv_weight: (24, 1024, 3, 3)
multi_feat_3_conv_3x3_conv_weight: (256, 128, 3, 3)
conv3_1_weight: (256, 128, 3, 3)
multi_feat_4_conv_3x3_relu_cls_pred_conv_weight: (16, 256, 3, 3)
relu4_3_loc_pred_conv_weight: (16, 512, 3, 3)
multi_feat_5_conv_3x3_conv_weight: (256, 128, 3, 3)
fc7_weight: (1024, 1024, 1, 1)
conv4_2_bias: (512,)
multi_feat_3_conv_3x3_relu_cls_pred_conv_weight: (24, 256, 3, 3)
multi_feat_3_conv_3x3_relu_cls_pred_conv_bias: (24,)
conv2_2_bias: (128,)
conv5_1_weight: (512, 512, 3, 3)
multi_feat_3_conv_1x1_conv_bias: (128,)
multi_feat_4_conv_3x3_relu_loc_pred_conv_bias: (16,)
conv1_1_weight: (64, 3, 3, 3)
multi_feat_4_conv_1x1_conv_bias: (128,)
conv3_1_bias: (256,)
multi_feat_5_conv_3x3_relu_loc_pred_conv_bias: (16,)
multi_feat_4_conv_1x1_conv_weight: (128, 256, 1, 1)
fc6_weight: (1024, 512, 3, 3)
multi_feat_5_conv_1x1_conv_weight: (128, 256, 1, 1)
conv3_2_bias: (256,)
conv5_2_bias: (512,)
relu4_3_cls_pred_conv_weight: (16, 512, 3, 3)
