From e92a0dbd79975ff6dd1d190b78182883ec0c3467 Mon Sep 17 00:00:00 2001 From: linqingke Date: Tue, 27 Oct 2020 19:43:50 +0800 Subject: [PATCH] mass and cnnctc readme fix. --- model_zoo/official/cv/cnnctc/README.md | 6 ++++-- model_zoo/official/cv/faster_rcnn/README.md | 2 ++ model_zoo/official/cv/psenet/README.md | 3 +++ model_zoo/official/nlp/mass/README.md | 6 ++++-- 4 files changed, 13 insertions(+), 4 deletions(-) diff --git a/model_zoo/official/cv/cnnctc/README.md b/model_zoo/official/cv/cnnctc/README.md index 0ec86bd8c5..380b0c7693 100644 --- a/model_zoo/official/cv/cnnctc/README.md +++ b/model_zoo/official/cv/cnnctc/README.md @@ -44,6 +44,8 @@ This is an example of training CNN+CTC model for text recognition on MJSynth and # [Dataset](#contents) +Note that you can run the scripts based on the dataset mentioned in original paper or widely used in relevant domain/network architecture. In the following sections, we will introduce how to run the scripts using the related dataset below. + The [MJSynth](https://www.robots.ox.ac.uk/~vgg/data/text/) and [SynthText](https://github.com/ankush-me/SynthText) dataset are used for model training. The [The IIIT 5K-word dataset](https://cvit.iiit.ac.in/research/projects/cvit-projects/the-iiit-5k-word-dataset) dataset is used for evaluation. - step 1: @@ -247,7 +249,7 @@ The model will be evaluated on the IIIT dataset, sample results and overall accu ### Training Performance -| Parameters | FasterRcnn | +| Parameters | CNNCTC | | -------------------------- | ----------------------------------------------------------- | | Model Version | V1 | | Resource | Ascend 910 ；CPU 2.60GHz，192cores；Memory，755G | @@ -265,7 +267,7 @@ The model will be evaluated on the IIIT dataset, sample results and overall accu ### Evaluation Performance -| Parameters | FasterRcnn | +| Parameters | CNNCTC | | ------------------- | --------------------------- | | Model Version | V1 | | Resource | Ascend 910 | diff --git a/model_zoo/official/cv/faster_rcnn/README.md b/model_zoo/official/cv/faster_rcnn/README.md index fa3efd9732..ba458b30d5 100644 --- a/model_zoo/official/cv/faster_rcnn/README.md +++ b/model_zoo/official/cv/faster_rcnn/README.md @@ -33,6 +33,8 @@ FasterRcnn is a two-stage target detection network,This network uses a region pr # Dataset +Note that you can run the scripts based on the dataset mentioned in original paper or widely used in relevant domain/network architecture. In the following sections, we will introduce how to run the scripts using the related dataset below. + Dataset used: [COCO2017]() - Dataset size：19G diff --git a/model_zoo/official/cv/psenet/README.md b/model_zoo/official/cv/psenet/README.md index 80bfff34d2..a9f76129e3 100644 --- a/model_zoo/official/cv/psenet/README.md +++ b/model_zoo/official/cv/psenet/README.md @@ -35,6 +35,9 @@ With the development of convolutional neural network, scene text detection techn Progressive Scale Expansion Network (PSENet) is a text detector which is able to well detect the arbitrary-shape text in natural scene. # [Dataset](#contents) + +Note that you can run the scripts based on the dataset mentioned in original paper or widely used in relevant domain/network architecture. In the following sections, we will introduce how to run the scripts using the related dataset below. + Dataset used: [ICDAR2015](https://rrc.cvc.uab.es/?ch=4&com=tasks#TextLocalization) A training set of 1000 images containing about 4500 readable words A testing set containing about 2000 readable words diff --git a/model_zoo/official/nlp/mass/README.md b/model_zoo/official/nlp/mass/README.md index 910dcaeaca..e6e4c87637 100644 --- a/model_zoo/official/nlp/mass/README.md +++ b/model_zoo/official/nlp/mass/README.md @@ -61,6 +61,8 @@ get the most possible prediction results. # Dataset +Note that you can run the scripts based on the dataset mentioned in original paper or widely used in relevant domain/network architecture. In the following sections, we will introduce how to run the scripts using the related dataset below. + Dataset used: - monolingual English data from News Crawl dataset(WMT 2019) for pre-training. - Gigaword Corpus(Graff et al., 2003) for Text Summarization. @@ -590,7 +592,7 @@ The comparisons between MASS and other baseline methods in terms of PPL on Corne | Model Version | v1 | | Resource | Ascend 910, cpu 2.60GHz, 192cores；memory, 755G | | uploaded Date | 05/24/2020 | -| MindSpore Version | 0.2.0 | +| MindSpore Version | 1.0.0 | | Dataset | News Crawl 2007-2017 English monolingual corpus, Gigaword corpus, Cornell Movie Dialog corpus | | Training Parameters | Epoch=50, steps=XXX, batch_size=192, lr=1e-4 | | Optimizer | Adam | @@ -613,7 +615,7 @@ The comparisons between MASS and other baseline methods in terms of PPL on Corne | Model Version | V1 | | Resource | Huawei 910 | | uploaded Date | 05/24/2020 | -| MindSpore Version | 0.2.0 | +| MindSpore Version | 1.0.0 | | Dataset | Gigaword corpus, Cornell Movie Dialog corpus | | batch_size | --- | | outputs | Sentence and probability |