- 30 3月, 2021 3 次提交
-
-
由 zlsh80826 提交于
* yolobox converter and plugin * yolobox unittest * add dynamic shape restriction * fix git merge log
-
由 Aurelius84 提交于
* Avoid raising warning while import paddle * fix segment fault of set_value * fix code style
-
由 wuhuanzhou 提交于
-
- 29 3月, 2021 9 次提交
-
-
由 niuliling123 提交于
-
由 tianshuo78520a 提交于
-
由 wanghuancoder 提交于
* modify API nn.Bilinear's doc, test=develop * modify API nn.Bilinear's doc, test=develop
-
由 liym27 提交于
-
由 ronnywang 提交于
-
由 Shang Zhizhou 提交于
* fix cmake model path * update cmake * fix unittest * fix unittest
-
由 Jiabin Yang 提交于
* give shape related contructor and reshape warning * change line num to fit ut * change ut to fit * remove useless code * call resize directly in constructor
-
由 zlsh80826 提交于
* add roi_align_plugin * add roi align unit_test * add roi align serialization * remove roi align static plugin because of batch dim issue * refine roi align unittest and add fp16/serialization * add trt roi align condition to op_teller * refine error message * remove unnecessary reshape layer
-
由 zlsh80826 提交于
* trt affine channel converter * add trt affine channel base test * add trt affine channel NHWC * remove asterisk for python2 compatibility * trt affine channel converter * add trt affine channel base test * add trt affine channel NHWC * remove asterisk for python2 compatibility * fix rebase * move LodTensor to Tensor * add dbg info * affine channel converter only support NCHW * scale,bias are parameters, use create_parameters api * reduce test input size to not exceed the timelimit of ci * refine affine channel unittest and add serialization/dynamic test * change super to InferencePassTest for python2 compatibility * change super to InferencePassTest for python2 compatibility * fix affine channel fp16 serialize setting
-
- 26 3月, 2021 5 次提交
-
-
由 cc 提交于
* Use layer to calculate output scale * add backward for moving_average_abs_max_scale and save output scales to op's attr
-
由 lilong12 提交于
* update, test=develop
-
由 zlsh80826 提交于
* add multiclass_nms * add multiclass_nms unittest * add default enable_tensorrt_oss option * refine multiclas nms unittest and add serialization/dynamic test * change super to InferencePassTest for python2 compatibility * refine multiclass nms unittest * move out dynamic shape test due to ci timelimit
-
由 Wilber 提交于
-
由 tianshuo78520a 提交于
* delete include framework.pb.h * fix error
-
- 25 3月, 2021 5 次提交
-
-
由 Chengmo 提交于
* fix zip py3 bug
-
由 Kaipeng Deng 提交于
-
由 Chen Weihang 提交于
* polish two error messages * polish details
-
由 Zhou Wei 提交于
-
由 niuliling123 提交于
-
- 24 3月, 2021 8 次提交
-
-
由 winter-wang 提交于
-
由 parap1uie-s 提交于
Fix default argument of nn.MaxPool3D()
-
由 Huihuang Zheng 提交于
Our old `loop_body` function may return single element when `loop_vars` just contains only 1 element, which can cause bug. The key point of this PR is forcing `loop_body` functions always return tuple.
-
由 Wojciech Uss 提交于
* fix cache key in concat oneDNN kernel * key simplified
-
由 Aurelius84 提交于
-
由 cc 提交于
* Refine saving output scale to infer program
-
由 Chen Weihang 提交于
-
由 ronnywang 提交于
-
- 23 3月, 2021 10 次提交
-
-
由 Zhou Wei 提交于
-
由 Chen Weihang 提交于
-
由 Feiyu Chan 提交于
-
由 Zhou Wei 提交于
* modify windows CI to VS2017 * modify windows CI to VS2017 * modify windows CI to VS2017
-
由 Wilber 提交于
-
由 niuliling123 提交于
* add relu forward kernel and backward kernel
-
由 Wojciech Uss 提交于
-
由 tianshuo78520a 提交于
* Delete fast_check_nan_inf * Delete run_fast_nan_inf_debug
-
由 Shang Zhizhou 提交于
* fix tensorrt output varible reshape * move padding shape x 1 x 1 in ernie to qkv and fc * update layer name * fix softmax when input is dynamic, fc not padding any more * fix varlen * move fc x_dim assert to op_teller
-
由 Qi Li 提交于
-