update docs

Summary: Pull Request resolved: fairinternal/detectron2#373

Differential Revision: D19553213

Pulled By: ppwwyyxx

fbshipit-source-id: 285396f9344c10758048a1de3101017931b0f98f

.circleci/config.yml

@@ -81,14 +81,14 @@ jobs:
       # Cache the venv directory that contains dependencies
       - restore_cache:
           keys:
-            - cache-key-{{ .Branch }}-ID-0
+            - cache-key-{{ .Branch }}-ID-20200124
 
       - <<: *install_dep
 
       - save_cache:
           paths:
             - ~/venv
-          key: cache-key-{{ .Branch }}-ID-0
+          key: cache-key-{{ .Branch }}-ID-20200124
 
       - <<: *install_detectron2
 

.github/ISSUE_TEMPLATE/unexpected-problems-bugs.md

@@ -35,7 +35,7 @@ Only in one of the two conditions we will help with it:
 
 ## Environment:
 
-Please paste the output of `python -m detectron2.utils.collect_env`.
+Run `python -m detectron2.utils.collect_env` in the environment where you observerd the issue, and paste the output.
 If detectron2 hasn't been successfully installed, use `python detectron2/utils/collect_env.py`.
 
 If your issue looks like an installation issue / environment issue,

INSTALL.md

@@ -97,15 +97,18 @@ Two possibilities:
 	you need to either install a different build of PyTorch (or build by yourself)
 	to match your local CUDA installation, or install a different version of CUDA to match PyTorch.
 
-* Detectron2 or PyTorch/torchvision is not built with the correct compute compatibility for the GPU model.
+* Detectron2 or PyTorch/torchvision is not built for the correct GPU architecture (compute compatibility).
 
-	The compute compatibility for PyTorch is available in `python -m detectron2.utils.collect_env`.
+	The GPU architecture for PyTorch/detectron2/torchvision is available in the "architecture flags" in
+	`python -m detectron2.utils.collect_env`.
 
-	The compute compatibility of detectron2/torchvision defaults to match the GPU found on the machine
-	during building, and can be controlled by `TORCH_CUDA_ARCH_LIST` environment variable during building.
+	The GPU architecture flags of detectron2/torchvision by default matches the GPU model detected
+	during building. This means the compiled code may not work on a different GPU model.
+	To overwrite the GPU architecture for detectron2/torchvision, use `TORCH_CUDA_ARCH_LIST` environment variable during building.
 
+	For example, `export TORCH_CUDA_ARCH_LIST=6.0,7.0` makes it work for both P100s and V100s.
 	Visit [developer.nvidia.com/cuda-gpus](https://developer.nvidia.com/cuda-gpus) to find out
-	the correct compute compatibility for your device.
+	the correct compute compatibility number for your device.
 
 </details>
 

MODEL_ZOO.md

@@ -4,8 +4,8 @@
 
 This file documents a large collection of baselines trained
 with detectron2 in Sep-Oct, 2019.
-All models were trained on [Big Basin](https://engineering.fb.com/data-center-engineering/introducing-big-basin-our-next-generation-ai-hardware/)
-servers with 8 NVIDIA V100 GPUs, with data-parallel sync SGD. The softwares in use were PyTorch 1.3, CUDA 9.2, cuDNN 7.4.2 or 7.6.3.
+All numbers were obtained on [Big Basin](https://engineering.fb.com/data-center-engineering/introducing-big-basin-our-next-generation-ai-hardware/)
+servers with 8 NVIDIA V100 GPUs & NVLink. The softwares in use were PyTorch 1.3, CUDA 9.2, cuDNN 7.4.2 or 7.6.3.
 You can programmataically access these models using [detectron2.model_zoo](https://detectron2.readthedocs.io/modules/model_zoo.html) APIs.
 
 #### How to Read the Tables

datasets/README.md

@@ -81,5 +81,9 @@ They are not needed for instance segmentation.
 VOC20{07,12}/
   Annotations/
   ImageSets/
+    Main/
+      trainval.txt
+      test.txt
+      # train.txt or val.txt, if you use these splits
   JPEGImages/
 ```

docs/requirements.txt

@@ -11,7 +11,8 @@ termcolor
 yacs
 tabulate
 cloudpickle
-Pillow
+Pillow==6.2.2
+protobuf
 git+git://github.com/facebookresearch/fvcore.git
 https://download.pytorch.org/whl/nightly/cpu/torch-1.3.0.dev20191010%2Bcpu-cp37-cp37m-linux_x86_64.whl
 https://download.pytorch.org/whl/nightly/cpu/torchvision-0.5.0.dev20191008%2Bcpu-cp37-cp37m-linux_x86_64.whl

docs/tutorials/models.md

@@ -16,6 +16,10 @@ in our model zoo.
 You can use a model by just `outputs = model(inputs)`.
 Next, we explain the inputs/outputs format used by the builtin models in detectron2.
 
+[DefaultPredictor](../modules/engine.html#detectron2.engine.defaults.DefaultPredictor)
+is a wrapper around model that provides the default behavior for regular inference. It includes model loading as
+well as preprocessing, and operates on single image rather than batches.
+
 
 ### Model Input Format