- 23 5月, 2019 3 次提交
-
-
由 Yanzhan Yang 提交于
-
由 Jiaying Zhao 提交于
-
由 Jiaying Zhao 提交于
* fix opencl no persistable bias in fusion conv op * delete log
-
- 22 5月, 2019 8 次提交
-
-
由 jameswu2014 提交于
-
由 Jiaying Zhao 提交于
* fix cpu conv_add and conv_add_relu * fix cpu conv_add and conv_add_relu
-
由 Yanzhan Yang 提交于
1. add optimize parameter to load function. 2. add transpose operation if the input of fetch op is not [0, 2, 3, 1]. (#1651)
-
由 Jiaying Zhao 提交于
-
由 xiebaiyuan 提交于* develop nearestinterp op fix bug in element add close #1647 * remove log remove log
-
由 zhaojiaying01 提交于
-
由 Yanzhan Yang 提交于
1. reshape output transpose should be 0, 1, 2, 3. 2.mps conv should be disabled when groups is larger than 1. 3. slice should re-tranpose its input if needed. (#1646)
-
由 Jiaying Zhao 提交于
* fix memcpy size in opencl fetch kernel * add opencl Scale op
-
- 21 5月, 2019 6 次提交
-
-
由 Yanzhan Yang 提交于
1.add groups to conv3x3. 2.add original size to tensor and tenture and adjust concat layer to handle tensor truncation logic. (#1643)
-
由 xiebaiyuan 提交于
-
由 NazgulLee 提交于
-
由 NazgulLee 提交于
-
由 Yanzhan Yang 提交于
-
由 jameswu2014 提交于
* V2-conv-hellocase pass & V1 verify-pass * V1 paralvl equal to 2 * softmax channel =2 bug * softmaxbug update2 * io update2 * V1-dwconv relu bug * opendevice bug fixed
-
- 20 5月, 2019 2 次提交
-
-
由 Yanzhan Yang 提交于
1.add flatten2, slice and nearest_interp op. 2.truncate tensor with more than 4 dimensions to 4. (#1634)
-
由 Yanzhan Yang 提交于
-
- 18 5月, 2019 1 次提交
-
-
由 Yanzhan Yang 提交于
1.parse tensor desc info from params file. 2.ensure tensor desc is consistent between params file and model file. (#1631)
-
- 17 5月, 2019 2 次提交
-
-
由 Jiaying Zhao 提交于
-
由 xiebaiyuan 提交于
-
- 16 5月, 2019 3 次提交
-
-
由 NazgulLee 提交于
-
由 xiebaiyuan 提交于
-
由 jameswu2014 提交于
* V2-conv-hellocase pass & V1 verify-pass * V1 paralvl equal to 2 * softmax channel =2 bug * softmaxbug update2 * io update2 * V1-dwconv relu bug
-
- 15 5月, 2019 2 次提交
-
-
由 Yanzhan Yang 提交于
-
由 Jiaying Zhao 提交于
* optimize GPU conv performance and structure * add CL macro for test_conv_gpu * fix build failure * change funtion name * change funtion name * fix load_when_predict mode in opencl * remove dafault opencl kernel path
-
- 13 5月, 2019 3 次提交
-
-
由 Jiaying Zhao 提交于
* optimize GPU conv performance and structure * add CL macro for test_conv_gpu * fix build failure * change funtion name * change funtion name * fix load_when_predict mode in opencl
-
由 qnqinan 提交于
* update concat and split kernel and related files in FPGA v2(v3) track * update * update * update kernel and related files in FPGA v2 track * update * update * update kernel and related files for static quantization in FPGA v2 track * update * update feed and fetch kernel in FPGA v2 track * update io file * update feed fetch and softmax kernel in FPGA v2 track
-
由 Shuai Yuan 提交于
* Update ocr test case * format code * format code
-
- 10 5月, 2019 4 次提交
-
-
由 Yanzhan Yang 提交于
-
由 Yanzhan Yang 提交于
-
由 Shuai Yuan 提交于
-
由 jameswu2014 提交于
* V2-conv-hellocase pass & V1 verify-pass * V1 paralvl equal to 2 * softmax channel =2 bug * softmaxbug update2 * io update2
-
- 09 5月, 2019 2 次提交
-
-
由 Yanzhan Yang 提交于
-
由 jameswu2014 提交于
* V2-conv-hellocase pass & V1 verify-pass * V1 paralvl equal to 2
-
- 08 5月, 2019 3 次提交
-
-
由 jameswu2014 提交于
-
由 Yanzhan Yang 提交于
* shift filter conversion process to loading phase * fix winograd edge case
-
由 qnqinan 提交于
* update concat and split kernel and related files in FPGA v2(v3) track * update * update * update kernel and related files in FPGA v2 track * update * update * update kernel and related files for static quantization in FPGA v2 track * update * update feed and fetch kernel in FPGA v2 track * update io file
-
- 07 5月, 2019 1 次提交
-
-
由 qnqinan 提交于
* update concat and split kernel and related files in FPGA v2(v3) track * update * update * update kernel and related files in FPGA v2 track * update * update * update kernel and related files for static quantization in FPGA v2 track * update * update feed and fetch kernel in FPGA v2 track
-