model scripts : BERT for TensorFlow

I try to run model script of BERT for TensorFlow(version 5) according to the quick start guide on NGC

  1. Clone the repository
    git clone https://github.com/NVIDIA/DeepLearningExamples
    cd DeepLearningExamples/TensorFlow/LanguageModeling/BERT

  2. Build the BERT TensorFlow NGC container.
    bash scripts/docker/build.sh

After doing it, I encouter error message like below.

root@wc414:~/DeepLearningExamples/TensorFlow/LanguageModeling/BERT# bash scripts/docker/build.sh
19.08-py3: Pulling from nvidia/tensorrtserver
Digest: sha256:438b6c2ddfd095faf3453f348c8639ea5be0c28a687a604d6f691f07469076c6
Status: Image is up to date for nvcr.io/nvidia/tensorrtserver:19.08-py3
nvcr.io/nvidia/tensorrtserver:19.08-py3
Sending build context to Docker daemon 6.619MB
Step 1/15 : ARG UBUNTU_VERSION=16.04
Step 2/15 : FROM ubuntu:{UBUNTU_VERSION} ---> 56bab49eef2e Step 3/15 : ENV DEBIAN_FRONTEND=noninteractive ---> Using cache ---> 47054b81c5f0 Step 4/15 : RUN if [ (cat /etc/os-release | grep ‘VERSION_ID=“16.04”’ | wc -l) -ne 0 ]; then apt-get update && apt-get install -y --no-install-recommends libcurl3-dev; elif [ $(cat /etc/os-release | grep ‘VERSION_ID=“18.04”’ | wc -l) -ne 0 ]; then apt-get update && apt-get install -y --no-install-recommends libcurl4-openssl-dev; else echo “Ubuntu version must be either 16.04 or 18.04” && exit 1; fi
—> Using cache
—> 9c993111ab54
Step 5/15 : RUN apt-get install -y --no-install-recommends software-properties-common autoconf automake build-essential curl git libopencv-dev libopencv-core-dev libtool pkg-config python python-dev
—> Using cache
—> 162a9a275f4a
Step 6/15 : RUN curl -O https://bootstrap.pypa.io/get-pip.py && python get-pip.py && rm get-pip.py
—> Using cache
—> 16afd14d5e4f
Step 7/15 : RUN pip install --upgrade setuptools grpcio-tools
—> Using cache
—> 4159bb2166c4
Step 8/15 : WORKDIR /workspace
—> Using cache
—> 0b09f84b50d3
Step 9/15 : COPY Makefile.client .
—> Using cache
—> 45afd197be52
Step 10/15 : COPY VERSION .
—> Using cache
—> 93cf54099256
Step 11/15 : COPY src src
—> Using cache
—> b7af0ec6273f
Step 12/15 : RUN make -j8 -f Makefile.client all
—> Using cache
—> 0f4b8a2bf84f
Step 13/15 : RUN mkdir -p /tmp/client/bin && cp build/image_client /tmp/client/bin/. && cp build/ensemble_image_client /tmp/client/bin/. && cp build/perf_client /tmp/client/bin/. && cp build/simple_client /tmp/client/bin/. && cp build/simple_string_client /tmp/client/bin/. && cp build/simple_sequence_client /tmp/client/bin/. && mkdir -p /tmp/client/lib && cp build/librequest.so /tmp/client/lib/. && cp build/librequest.a /tmp/client/lib/. && mkdir -p /tmp/client/include && cp build/src/core/api.pb.h /tmp/client/include/. && cp build/src/core/model_config.pb.h /tmp/client/include/. && cp build/src/core/request_status.pb.h /tmp/client/include/. && cp build/src/core/server_status.pb.h /tmp/client/include/. && cp src/clients/c++/request.h /tmp/client/include/. && cp src/clients/c++/request_http.h /tmp/client/include/. && cp src/clients/c++/request_grpc.h /tmp/client/include/. && mkdir -p /tmp/client/python && cp src/clients/python/image_client.py /tmp/client/python/. && cp src/clients/python/ensemble_image_client.py /tmp/client/python/. && cp src/clients/python/grpc_image_client.py /tmp/client/python/. && cp src/clients/python/simple_client.py /tmp/client/python/. && cp src/clients/python/simple_string_client.py /tmp/client/python/. && cp src/clients/python/simple_sequence_client.py /tmp/client/python/. && cp build/dist/dist/*.whl /tmp/client/python/. && export VERSION=cat /workspace/VERSION && (cd /tmp/client && tar zcf /workspace/v$VERSION.clients.tar.gz )
—> Using cache
—> e74ae59e421d
Step 14/15 : COPY qa/images/mug.jpg images/mug.jpg
—> Using cache
—> 717d88148b90
Step 15/15 : RUN pip install --upgrade build/dist/dist/tensorrtserver-
.whl numpy pillow
—> Using cache
—> a0794daf3193
Successfully built a0794daf3193
Successfully tagged tensorrtserver_client:latest
/root/DeepLearningExamples/TensorFlow/LanguageModeling/BERT
Sending build context to Docker daemon 8.044MB
Step 1/18 : ARG FROM_IMAGE_NAME=nvcr.io/nvidia/tensorflow:19.08-py3
Step 2/18 : FROM ${FROM_IMAGE_NAME}
—> be978d32a5c3
Step 3/18 : RUN apt-get update && apt-get install -y pbzip2 pv bzip2 libcurl3
—> Using cache
—> 48400de8b584
Step 4/18 : RUN pip install toposort networkx pytest nltk tqdm html2text progressbar
—> Using cache
—> 243fd375c39d
Step 5/18 : WORKDIR /workspace
—> Using cache
—> 797a55d42f4c
Step 6/18 : RUN git clone https://github.com/openai/gradient-checkpointing.git
—> Using cache
—> f66b4d77151f
Step 7/18 : RUN git clone https://github.com/attardi/wikiextractor.git
—> Using cache
—> 5ae7dedbbea6
Step 8/18 : RUN git clone https://github.com/soskek/bookcorpus.git
—> Using cache
—> 4ccf50bddb06
Step 9/18 : RUN git clone https://github.com/titipata/pubmed_parser
—> Using cache
—> 8e95d1fd49be
Step 10/18 : RUN pip3 install /workspace/pubmed_parser
—> Using cache
—> 03cc6c2673f5
Step 11/18 : COPY --from=trt /workspace/install/ /workspace/install/
invalid from flag value trt: pull access denied for trt, repository does not exist or may require ‘docker login’: denied: requested access to the resource is denied

I don’t know what is wrong, please advice me.

ps) I already logged nvcr.io in through API Key.

Thanks,
Brian