Comparison Data Description

Before tensor comparison, prepare the data by referring to Table 1.

Select files for My Output as follows:

Offline model file: required if to compare the dump data of a model running on the Ascend AI Processor with Ground Truths.
Quantization fusion file: Required if to compare quantized and non-quantized dump data.

**Table 1** Data preparation for tensor comparison
No.	Data to Be Compared (My Output)	Standard Data (Ground Truth)	Model File/Quantization Fusion File
1	Dump data of the non-quantized offline model running on the Ascend AI Processor	Dump data or .npy file of the non-quantized Caffe model	Non-quantized offline model file (.om)
2	Dump data of the quantized offline model running on the Ascend AI Processor	Dump data or .npy file of the non-quantized Caffe model	Quantized offline model file (.om) Quantization fusion pattern file (.json) after model compression
3	Dump data or .npy file of the quantized Caffe model	Dump data or .npy file of the non-quantized Caffe model	Quantization fusion pattern file (.json) after model compression
4	Dump data of the quantized offline model running on the Ascend AI Processor	Dump data or .npy file of the quantized Caffe model	Quantized offline model file (.om)
5	Dump data of the non-quantized offline model running on the Ascend AI Processor	Dump data or .npy file of the non-quantized TensorFlow model	Non-quantized offline model file (.om)
6	Dump data of the model running on the Ascend AI Processor	Dump data of the model running on the Ascend AI Processor	-

Parent topic: Tensor Comparison