| /OK3568_Linux_fs/kernel/net/ipv4/ |
| H A D | tcp_lp.c | 87 u32 inference; member 109 lp->inference = 0; in tcp_lp_init() 277 lp->inference = 3 * delta; in tcp_lp_pkts_acked() 280 if (lp->last_drop && (now - lp->last_drop < lp->inference)) in tcp_lp_pkts_acked()
|
| /OK3568_Linux_fs/external/rknn-toolkit2/examples/functions/dynamic_input/ |
| H A D | test.py | 89 outputs = rknn.inference(inputs=[img2], data_format=['nchw']) 96 outputs = rknn.inference(inputs=[img3], data_format=['nchw'])
|
| /OK3568_Linux_fs/docs/en/Common/NPU/rknn-toolkit2/ |
| H A D | changelog-1.4.0.txt | 93 4)修复了caffe slice丢弃了其中一个输出的inference bug 95 4. 弃置了reorder_channel的config设置,由用户自行保证inference输入数据的channel正确性
|
| H A D | RKNNToolKit2_API_Difference_With_Toolkit1-1.4.0.md | 264 ## rknn.inference 267 inference(inputs, 274 inference(inputs,
|
| /OK3568_Linux_fs/docs/cn/Common/NPU/rknn-toolkit2/ |
| H A D | changelog-1.4.0.txt | 93 4)修复了caffe slice丢弃了其中一个输出的inference bug 95 4. 弃置了reorder_channel的config设置,由用户自行保证inference输入数据的channel正确性
|
| H A D | RKNNToolKit2_API_Difference_With_Toolkit1-1.4.0.md | 264 ## rknn.inference 267 inference(inputs, 274 inference(inputs,
|
| /OK3568_Linux_fs/external/rknn-toolkit2/doc/ |
| H A D | RKNNToolKit2_API_Difference_With_Toolkit1-1.5.0.md | 267 ## rknn.inference 270 inference(inputs, 277 inference(inputs,
|
| H A D | changelog-1.5.0.txt | 424 4)修复了caffe slice丢弃了其中一个输出的inference bug 426 4. 弃置了reorder_channel的config设置,由用户自行保证inference输入数据的channel正确性
|
| /OK3568_Linux_fs/external/rknpu2/examples/rknn_yolov5_android_apk_demo/ |
| H A D | README.md | 16 - JAVA: com.rockchip.gpadc.demo: 读取camera输入,并调用jni进行inference,并将结果显示出来 18 - JNI: 调用rknnrt进行实际inference
|
| /OK3568_Linux_fs/external/rknn-toolkit2/examples/functions/hybrid_quant/ |
| H A D | step2.py | 51 outputs = rknn.inference(inputs=[img])
|
| /OK3568_Linux_fs/yocto/meta-openembedded/meta-python/recipes-devtools/python/ |
| H A D | python3-astroid_2.11.3.bb | 1 SUMMARY = "An abstract syntax tree for Python with inference support."
|
| /OK3568_Linux_fs/external/rknn-toolkit2/examples/functions/multi_input_test/ |
| H A D | test.py | 64 …outputs = rknn.inference(inputs=[img, input2, input3, img_gray], data_format=['nhwc', 'nchw', 'nch…
|
| /OK3568_Linux_fs/external/rknn-toolkit2/examples/tflite/mobilenet_v1_qat/ |
| H A D | test.py | 73 outputs = rknn.inference(inputs=[img])
|
| /OK3568_Linux_fs/external/rknn-toolkit2/examples/caffe/mobilenet_v2/ |
| H A D | test.py | 73 outputs = rknn.inference(inputs=[img])
|
| /OK3568_Linux_fs/kernel/drivers/misc/habanalabs/ |
| H A D | Kconfig | 14 designed to accelerate Deep Learning inference and training workloads.
|
| /OK3568_Linux_fs/external/rknn-toolkit2/examples/functions/model_pruning/ |
| H A D | test.py | 90 outputs = rknn.inference(inputs=[img])
|
| /OK3568_Linux_fs/external/rknn-toolkit2/examples/tflite/mobilenet_v1/ |
| H A D | test.py | 73 outputs = rknn.inference(inputs=[img])
|
| /OK3568_Linux_fs/external/rknn-toolkit2/examples/functions/batch_size/ |
| H A D | test.py | 81 outputs = rknn.inference(inputs=[img])
|
| /OK3568_Linux_fs/external/rknn-toolkit2/examples/functions/mmse/ |
| H A D | test.py | 86 outputs = rknn.inference(inputs=[img])
|
| /OK3568_Linux_fs/external/rknn-toolkit2/examples/functions/board_test/ |
| H A D | test.py | 100 outputs = rknn.inference(inputs=[img])
|
| /OK3568_Linux_fs/external/rknn-toolkit2/rknn_toolkit_lite2/examples/inference_with_lite/ |
| H A D | test.py | 98 outputs = rknn_lite.inference(inputs=[img])
|
| /OK3568_Linux_fs/external/rknn-toolkit2/examples/pytorch/resnet18/ |
| H A D | test.py | 96 outputs = rknn.inference(inputs=[img])
|
| /OK3568_Linux_fs/external/rknn-toolkit2/examples/pytorch/resnet18_qat/ |
| H A D | test.py | 98 outputs = rknn.inference(inputs=[img])
|
| /OK3568_Linux_fs/external/rknn-toolkit2/examples/darknet/yolov3_416x416/ |
| H A D | test.py | 70 outputs = rknn.inference(inputs=[img])
|
| /OK3568_Linux_fs/yocto/poky/meta/recipes-support/db/db/ |
| H A D | 0001-configure-Add-explicit-tag-options-to-libtool-invoca.patch | 6 This helps cross compile when tag inference via heuristics
|