Merge pull request #1267 from kermitt2/feature/docker-evaluation-image

End to end evaluation docker image follow-up

Author: lfoppiano

.github/workflows/ci-build-manual-eval.yml

@@ -1,4 +1,4 @@
-name: Build and push a full docker image
+name: Build and push the Grobid ent to end evaluation docker image
 
 on:
   workflow_dispatch:

Dockerfile.evaluation

@@ -1,7 +1,12 @@
 ## Grobid evaluation image
-## ------
+# ------
 # https://grobid.readthedocs.io/en/latest/End-to-end-evaluation/
-# NOTE: To match the exact evaluation published in the Grobid documentation is necessary to have a running Biblio-glutton instance
+# NOTE: To match the exact evaluation published in the Grobid documentation is necessary to have a
+# running Biblio-glutton instance
+#
+# A project using this image can be found here: https://huggingface.co/spaces/lfoppiano/grobid-evaluation
+# Please notice that the evaluation is run through a python script that runs all the needed commands
+# TODO: upload the evaluation in Markdown somewhere
 
 FROM lfoppiano/grobid:0.8.2-RC1-full as runtime
 
@@ -11,7 +16,7 @@ ENV LANG C.UTF-8
 USER root
 
 RUN apt-get update && \
-    apt-get -y --no-install-recommends install unzip wget
+    apt-get -y --no-install-recommends install unzip wget git git-lfs
 
 WORKDIR /opt/grobid
 
@@ -27,33 +32,24 @@ COPY grobid-core/ ./grobid-core/
 COPY grobid-service/ ./grobid-service/
 COPY grobid-trainer/ ./grobid-trainer/
 
-# Setting DL-powered configuration
+# Setting DL-powered configuration + biblio-glutton
 COPY grobid-home/config/grobid-evaluation.yaml grobid-home/config/config.yaml
 
 RUN rm -rf /opt/grobid/grobid-home/models/*-with_ELMo \
     && mkdir /opt/grobid/evaluation
 
-# Download evaluation data
+# Download evaluation data (For space reasons, we are not downloading the evaluation data) \
+# See https://huggingface.co/spaces/lfoppiano/grobid-evaluation/blob/main/Dockerfile
 WORKDIR /opt/grobid/evaluation
-RUN wget https://zenodo.org/records/3873702/files/biorxiv-10k-test-2000.zip -O biorxiv-10k-test-2000.zip \
-    && unzip biorxiv-10k-test-2000.zip -d biorxiv-10k-test-2000 \
-    && wget https://zenodo.org/records/7708580/files/eLife_984.zip -O eLife_984.zip \
-    && unzip eLife_984.zip -d eLife_984 \
-    && wget https://zenodo.org/records/7708580/files/PLOS_1000.zip -O PLOS_1000.zip \
-    && unzip PLOS_1000.zip -d PLOS_1000 \
-    && wget https://zenodo.org/records/7708580/files/PMC_sample_1943.zip -O PMC_sample_1943.zip \
-    && unzip PMC_sample_1943.zip -d PMC_sample_1943 \
-    && rm *.zip
-
-#RUN wget -q https://zenodo.org/records/7708580/files/PMC_sample_1943.zip -O PMC_sample_1943.zip \
-#    && unzip PMC_sample_1943.zip -d PMC_sample_1943 \
-#    && rm *.zip
+#RUN git lfs install && git clone --depth 1 https://huggingface.co/datasets/sciencialab/grobid-evaluation evaluation
+#RUN chmod -R uog+rw /opt/grobid/evaluation
 
 VOLUME ["/opt/grobid/grobid-home/tmp"]
 
 WORKDIR /opt/grobid
 
 CMD ["/bin/bash", "-c", "./gradlew jatsEval -Pp2t=/opt/grobid/evaluation/PMC_sample_1943 -Prun=1 -PfileRatio=1; ./gradlew jatsEval -Pp2t=/opt/grobid/evaluation/biorxiv-10k-test-2000 -Prun=1 -PfileRatio=1; ./gradlew jatsEval -Pp2t=/opt/grobid/evaluation/eLife_984 -Prun=1 -PfileRatio=1; ./gradlew jatsEval -Pp2t=/opt/grobid/evaluation/PLOS_1000 -Prun=1 -PfileRatio=1;"]
+#CMD ["/bin/bash", "-c", "./gradlew jatsEval -Pp2t=/opt/grobid/evaluation/PMC_sample_1943 -Prun=1 -PfileRatio=1;"]
 
 LABEL \
     authors="The contributors" \

grobid-home/config/grobid-evaluation.yaml

@@ -67,7 +67,7 @@ grobid:
     # DeLFT global parameters
     # delft installation path if Deep Learning architectures are used to implement one of the sequence labeling model,
     # embeddings are usually compiled as lmdb under delft/data (this parameter is ignored if only featured-engineered CRF are used)
-    install: "../delft"
+    install: "/opt/delft"
     pythonVirtualEnv:
 
   wapiti: