diff --git a/docs/source_en/benchmark.md b/docs/source_en/benchmark.md index 13a2238d6772fad14aa598ba6ffa75330a816575..446ddac3bbf78f04ee7de7c4ac58c227a8a679b9 100644 --- a/docs/source_en/benchmark.md +++ b/docs/source_en/benchmark.md @@ -16,7 +16,7 @@ For details about the MindSpore pre-trained model, see [Model Zoo](https://gitee | | | | | Ascend: 16 * Ascend 910 </br> CPU:384 Cores | Mixed | 256 | 32768 images/sec | 0.96 | 1. The preceding performance is obtained based on ModelArts, the HUAWEI CLOUD AI development platform. It is the average performance obtained by the Ascend 910 AI processor during the overall training process. -2. For details about other open source frameworks, see [ResNet-50 v1.5 for TensorFlow](https://github.com/NVIDIA/DeepLearningExamples/tree/master/TensorFlow/Classification/RN50v1.5#nvidia-dgx-2-16x-v100-32g). +2. For details about other open source frameworks, see [ResNet-50 v1.5 for TensorFlow](https://github.com/NVIDIA/DeepLearningExamples/tree/master/TensorFlow/Classification/ConvNets/resnet50v1.5). ### BERT @@ -26,4 +26,4 @@ For details about the MindSpore pre-trained model, see [Model Zoo](https://gitee | | | | | Ascend: 8 * Ascend 910 </br> CPU:192 Cores | Mixed | 96 | 2069 sentences/sec | 0.96 | 1. The preceding performance is obtained based on ModelArts, the HUAWEI CLOUD AI development platform. The network contains 24 hidden layers, the sequence length is 128 tokens, and the vocabulary contains 21128 tokens. -2. For details about other open source frameworks, see [BERT For TensorFlow](https://github.com/NVIDIA/DeepLearningExamples/tree/master/TensorFlow/LanguageModeling/BERT). \ No newline at end of file +2. For details about other open source frameworks, see [BERT For TensorFlow](https://github.com/NVIDIA/DeepLearningExamples/tree/master/TensorFlow/LanguageModeling/BERT). diff --git a/docs/source_zh_cn/benchmark.md b/docs/source_zh_cn/benchmark.md index e401cfde8770e8bf7c54880051fee77c8d1f70f8..2da80e81d965bf69f532e01dc62aadc14ff017d5 100644 --- a/docs/source_zh_cn/benchmark.md +++ b/docs/source_zh_cn/benchmark.md @@ -15,7 +15,7 @@ | | | | | Ascend: 16 * Ascend 910 </br> CPU:384 Cores | Mixed | 256 | 32768 images/sec | 0.96 | 1. 以上数æ®åŸºäºŽåŽä¸ºäº‘AIå¼€å‘å¹³å°ModelArts测试获得,是è®ç»ƒè¿‡ç¨‹æ•´ä½“下沉至Ascend 910 AI处ç†å™¨æ‰§è¡Œæ‰€å¾—çš„å¹³å‡æ€§èƒ½ã€‚ -2. 业界其他开æºæ¡†æž¶æ•°æ®å¯å‚考:[ResNet-50 v1.5 for TensorFlow](https://github.com/NVIDIA/DeepLearningExamples/tree/master/TensorFlow/Classification/RN50v1.5#nvidia-dgx-2-16x-v100-32g)。 +2. 业界其他开æºæ¡†æž¶æ•°æ®å¯å‚考:[ResNet-50 v1.5 for TensorFlow](https://github.com/NVIDIA/DeepLearningExamples/tree/master/TensorFlow/Classification/ConvNets/resnet50v1.5)。 ### BERT @@ -25,4 +25,4 @@ | | | | | Ascend: 8 * Ascend 910 </br> CPU:192 Cores | Mixed | 96 | 2069 sentences/sec | 0.96 | 1. 以上数æ®åŸºäºŽåŽä¸ºäº‘AIå¼€å‘å¹³å°ModelArts测试获得,其ä¸ç½‘络包å«24个éšè—层,å¥é•¿ä¸º128个token,å—典表包å«21128个token。 -2. 业界其他开æºæ¡†æž¶æ•°æ®å¯å‚考:[BERT For TensorFlow](https://github.com/NVIDIA/DeepLearningExamples/tree/master/TensorFlow/LanguageModeling/BERT)。 \ No newline at end of file +2. 业界其他开æºæ¡†æž¶æ•°æ®å¯å‚考:[BERT For TensorFlow](https://github.com/NVIDIA/DeepLearningExamples/tree/master/TensorFlow/LanguageModeling/BERT)。