Merge branch 'master' into master

.github/ISSUE_TEMPLATE/issue-template.md → ISSUE_TEMPLATE.md

@@ -6,7 +6,7 @@ about: Bug and Feature Report
 
 Before you open an issue, please make sure you have tried the following steps:
 
-1. Make sure your ENV is the same with (https://mace.readthedocs.io/en/latest/installation/env_requirement.html).
+1. Make sure your **environment** is the same with (https://mace.readthedocs.io/en/latest/installation/env_requirement.html).
 2. Have you ever read the document for your usage?
 3. The form below must be filled.
 
@@ -14,10 +14,11 @@ Before you open an issue, please make sure you have tried the following steps:
 
 ### System information
 - **OS Platform and Distribution (e.g., Linux Ubuntu 16.04)**:
-- **NDK version(e.g. 15c)**:
+- **NDK version(e.g., 15c)**:
+- **GCC version(if compiling for host, e.g., 5.4.0)**:
 - **MACE version (Use the command: git describe --long --tags)**:
 - **Python version(2.7)**: 
-- **Bazel version (e.g. 0.13.0)**:
+- **Bazel version (e.g., 0.13.0)**:
 
 ### Model deploy file (*.yml)
 ```yaml
@@ -28,16 +29,17 @@ Before you open an issue, please make sure you have tried the following steps:
 A clear and concise description of what the bug is.
 
 ### To Reproduce
-Steps to reproduce the behavior:
+Steps to reproduce the problem:
 ```bash
 1. cd /path/to/mace
 2. python tools/converter.py convert --config_file=/path/to/your/model_deployment_file
 ```
 
 ### Error information / logs
+Please include the **full** log and/or traceback here.
 ```bash
 LOGs
 ```
 
 ### Additional context
-Add any other context about the problem here.
+Add any other context about the problem here, e.g., what you have modified about the code.

mace/kernels/opencl/depthwise_conv.cc

@@ -38,7 +38,7 @@ std::vector<uint32_t> LocalWS(const uint32_t *gws, const uint32_t kwg_size) {
                                   kwg_size / lws[1]);
     }
   }
-  lws[0] = std::max<uint32_t>(lws[0], 1);
+  lws[0] = std::max<uint32_t>(std::min<uint32_t>(lws[0], kwg_size / lws[1]), 1);
   const uint32_t lws_size = lws[0] * lws[1];
   lws[2] = std::min<uint32_t>((cache_size / kernel_cache_size / lws_size) * 4,
                               gws[2]);

mace/libmace/BUILD

@@ -92,7 +92,8 @@ genrule(
           "$@ " +
           "$$tmp_mri_file);" +
           "$(AR) -M <$$tmp_mri_file;" +
-          "rm -rf $$tmp_mri_file;",
+          "rm -rf $$tmp_mri_file;" +
+          "$(STRIP) -x $@;",
     tools = ["//mace/python/tools:archive_static_lib"],
     visibility = ["//visibility:public"],
 )