[Test refactor 5/5] Build docker images (#15729)

docker/transformers-pytorch-gpu/Dockerfile

@@ -1,30 +1,25 @@
-FROM nvidia/cuda:10.2-cudnn7-devel-ubuntu18.04
+FROM nvidia/cuda:11.2.2-cudnn8-runtime-ubuntu20.04
 LABEL maintainer="Hugging Face"
-LABEL repository="transformers"
 
-RUN apt update && \
-    apt install -y bash \
-                   build-essential \
-                   git \
-                   curl \
-                   ca-certificates \
-                   python3 \
-                   python3-pip && \
-    rm -rf /var/lib/apt/lists
+ARG DEBIAN_FRONTEND=noninteractive
 
-RUN python3 -m pip install --no-cache-dir --upgrade pip && \
-    python3 -m pip install --no-cache-dir \
-    mkl \
-    torch
+RUN apt update
+RUN apt install -y git libsndfile1-dev tesseract-ocr espeak-ng python3 python3-pip ffmpeg
+RUN python3 -m pip install --no-cache-dir --upgrade pip
 
-RUN git clone https://github.com/NVIDIA/apex
-RUN cd apex && \
-    python3 setup.py install && \
-    pip install -v --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" ./
+ARG REF=master
+RUN git clone https://github.com/huggingface/transformers && cd transformers && git checkout $REF
+RUN python3 -m pip install --no-cache-dir -e ./transformers[dev,onnxruntime]
 
-WORKDIR /workspace
-COPY . transformers/
-RUN cd transformers/ && \
-    python3 -m pip install --no-cache-dir .
+# If set to nothing, will install the latest version
+ARG PYTORCH=''
 
-CMD ["/bin/bash"]
+RUN [ ${#PYTORCH} -gt 0 ] && VERSION='torch=='$PYTORCH'.*' ||  VERSION='torch'; python3 -m pip install --no-cache-dir -U $VERSION
+RUN python3 -m pip uninstall -y tensorflow flax
+
+RUN python3 -m pip install --no-cache-dir torch-scatter -f https://data.pyg.org/whl/torch-$(python3 -c "from torch import version; print(version.__version__.split('+')[0])")+cpu.html
+RUN python3 -m pip install --no-cache-dir git+https://github.com/facebookresearch/detectron2.git pytesseract https://github.com/kpu/kenlm/archive/master.zip
+
+# When installing in editable mode, `transformers` is not recognized as a package.
+# this line must be added in order for python to be aware of transformers.
+RUN cd transformers && python3 setup.py develop