Henry
> I have met this problem yesterday. I fix it by reducing the version of TensorFlow. Thanks. Do you join a competition called “2019 remote sensing”...? How about build a...
> > I have met this problem yesterday. I fix it by reducing the version of TensorFlow. > > Thanks！It worked! But a new problem came up: out of memory......
> I also met the same problem. After seeing the source code, I found It's no need to write anything after "pretrained_weights" in the configuration JSON File. These weights not...
这有点牛皮了。。。
> @hcnhatnam enen, i am checking. 华为书法识别？留个联系方式交流下吧
> I found that by reducing the anchors can somehow alleviate this problem, you can reduce some angels or ratios in R-DFPN_FPN_Tensorflow/libs/configs/cfgs.py ANCHOR_ANGLES = [-90, -75, -60, -45, -30, -15]...
Here is the result of epoch 1, I don't know why the prediction is nearly all class 1, how to fix the problem? +------------+-----+-------+--------+-------+ | class | gts | dets...
> Hi, we are working on ubuntu 18.04 with NVIDIA GeForce RTX 2080 with driver version 418.56. cuda version 10.1. > Is caffe compatible with this gpu and driver? It...
the code in BUILD_ is as below: ``` load("@rules_cc//cc:defs.bzl", "cc_library", "cc_test") load("//tools:cpplint.bzl", "cpplint") package(default_visibility = ["//visibility:public"]) cc_test( name = "camera_app_obstacle_camera_perception_test", size = "medium", srcs = ["camera_app_obstacle_camera_perception_test.cc"], deps = [ "//modules/perception/camera/app:obstacle_camera_perception",...