模型推理遇到问题

只看该作者 · 发表于 2020-5-19 12:10:49

candela4rk 发表于 2020-5-19 12:04
好像找不到npu，有验证指令吗，我获取不到设备id......

lsusb 看下有没有 0x2207开头的。
你这个应该不是没NPU，之前不是都list出来了。只是你没指定用哪个NPU而已。
我们是支持多计算棒并行计算的，如果同时插了好几个，这时候不就得手动指定

只看该作者 · 发表于 2020-5-19 17:04:41

jefferyzhang 发表于 2020-5-19 12:02
没看明白。。。
现在的错误是啥？如果init runtime说没设备，就是你的init runtime的参数没填对，可以看 ...

我用API，查看设备数是0
E RKNNAPI: rknn_find_devices fail!
n_devices = 0

#include <stdio.h>

#include "rknn_api.h"

#include <pthread.h>



int main()

{

    rknn_devices_id devids;

    rknn_find_devices(&devids);

    printf("n_devices = %d\n", devids.n_devices);

    for (int i = 0; i < devids.n_devices; i++)

    {

        printf("%d: type=%s, id=%s\n", i, devids.types[i], devids.ids[i]);

    }

    return 0;

}
复制代码

只看该作者 · 发表于 2020-5-19 17:06:25

jefferyzhang 发表于 2020-5-19 12:10
lsusb 看下有没有 0x2207开头的。
你这个应该不是没NPU，之前不是都list出来了。只是你没指定用哪个NPU而 ...

有
Bus 002 Device 003: ID 2207:0019 Fuzhou Rockchip Electronics Company

只看该作者 · 发表于 2020-5-19 17:33:07

从你lsusb结果来看都是正常的。
请问下你的开发版是谁家的，型号是什么，系统是什么，是3399pro还是1808计算棒

只看该作者 · 发表于 2020-5-19 17:41:00

jefferyzhang 发表于 2020-5-19 17:33
从你lsusb结果来看都是正常的。
请问下你的开发版是谁家的，型号是什么，系统是什么，是3399pro还是1808计 ...

产品名称：TB-RK3399ProDs
产品型号：T331040232D
系统: Debian10

只看该作者 · 发表于 2020-5-19 17:44:41

jefferyzhang 发表于 2020-5-19 17:33
从你lsusb结果来看都是正常的。
请问下你的开发版是谁家的，型号是什么，系统是什么，是3399pro还是1808计 ...

#include <stdio.h>

#include "rknn_api.h"

#include <pthread.h>

#include <fstream>



int main()

{

   rknn_context ctx = 0;

   const char *model_path = "/home/toybrick/rknn_api/mobilenet_ssd.rknn";

   FILE *fp = fopen(model_path, "rb");

    if(fp == NULL) {

        printf("fopen %s fail!\n", model_path);

        return -1;

    }

    fseek(fp, 0, SEEK_END);

    int model_len = ftell(fp);

    void *model = malloc(model_len);

    fseek(fp, 0, SEEK_SET);

    if(model_len != fread(model, 1, model_len, fp)) {

        printf("fread %s fail!\n", model_path);

        free(model);

        return -1;

    }

   rknn_init(&ctx, model, model_len, RKNN_FLAG_PRIOR_MEDIUM);

   rknn_sdk_version version;

   rknn_query(ctx, RKNN_QUERY_SDK_VERSION, &version, sizeof(rknn_sdk_version));

   printf("api version: %s\n", version.api_version);

   printf("driver version: %s\n", version.drv_version);

    rknn_devices_id devids;

    rknn_find_devices(&devids);

    printf("n_devices = %d\n", devids.n_devices);

    for (int i = 0; i < devids.n_devices; i++)

    {

        printf("%d: type=%s, id=%s\n", i, devids.types[i], devids.ids[i]);

    }

    return 0;

}
复制代码

输出：
E RKNNAPI: rknn_init, driver open fail! ret = -9(ERROR_PIPE)!
E RKNNAPI: rknn_query, context = nullptr!
api version:
driver version: �m��
E RKNNAPI: rknn_find_devices fail!
n_devices = 0

只看该作者 · 发表于 2020-5-19 18:27:27

执行命令：npu_transfer_devices
确认下设备是否存在。

只看该作者 · 发表于 2020-5-20 10:12:19

addy 发表于 2020-5-19 18:27
执行命令：npu_transfer_devices
确认下设备是否存在。

我更新驱动以后，npu_transfer_proxy devices输出：
List of ntb devices attached
9cd15daa2683fa8f 2c41d4f0 USB_DEVICE

C++代码输出：
D RKNNAPI: ==============================================
D RKNNAPI: RKNN VERSION:
D RKNNAPI: API: 1.3.0 (c5654ea build: 2019-12-25 14:12:00)
D RKNNAPI: DRV: 1.3.1 (6ebb4d7 build: 2020-01-02 09:37:58)
D RKNNAPI: ==============================================
api version: 1.3.0 (c5654ea build: 2019-12-25 14:12:00)
driver version: 1.3.1 (6ebb4d7 build: 2020-01-02 09:37:58)
n_devices = 1
0: type=USB_DEVICE, id=9cd15daa2683fa8f

wiki的推理程序报错：
-->loading model
loading model done
--> Init runtime environment
E Only support ntb mode on ARM64 platform. But can not find device with ntb mode.
E Catch exception when init runtime!
E Traceback (most recent call last):
E File "rknn/api/rknn_base.py", line 1042, in rknn.api.rknn_base.RKNNBase.init_runtime
E File "rknn/api/rknn_runtime.py", line 168, in rknn.api.rknn_runtime.RKNNRuntime.__init__
E File "rknn/api/rknn_platform_utils.py", line 285, in rknn.api.rknn_platform_utils.start_ntp_or_adb
E Exception: Init runtime environment failed!
E Current device id is: 9cd15daa2683fa8f
E Devices connected:
E ['9cd15daa2683fa8f']
Init runtime environment failed

只看该作者 · 发表于 2020-5-20 10:30:48

jefferyzhang 发表于 2020-5-19 17:33
从你lsusb结果来看都是正常的。
请问下你的开发版是谁家的，型号是什么，系统是什么，是3399pro还是1808计 ...

回到开始的问题了，模型转换也出错了：
--> Loading model
W:tensorflow:From /home/toybrick/.local/lib/python3.7/site-packages/onnx_tf/handlers/backend/ceil.py:10: The name tf.ceil is deprecated. Please use tf.math.ceil instead.

W:tensorflow:From /home/toybrick/.local/lib/python3.7/site-packages/onnx_tf/handlers/backend/depth_to_space.py:12: The name tf.depth_to_space is deprecated. Please use tf.compat.v1.depth_to_space instead.

W:tensorflow:
The TensorFlow contrib module will not be included in TensorFlow 2.0.
For more information, please see:
  * https://github.com/tensorflow/co ... 7-contrib-sunset.md
  * https://github.com/tensorflow/addons
  * https://github.com/tensorflow/io (for I/O related ops)
If you depend on functionality not listed there, please file an issue.

W:tensorflow:From /home/toybrick/.local/lib/python3.7/site-packages/onnx_tf/handlers/backend/log.py:10: The name tf.log is deprecated. Please use tf.math.log instead.

W:tensorflow:From /home/toybrick/.local/lib/python3.7/site-packages/onnx_tf/handlers/backend/random_normal.py:9: The name tf.random_normal is deprecated. Please use tf.random.normal instead.

W:tensorflow:From /home/toybrick/.local/lib/python3.7/site-packages/onnx_tf/handlers/backend/random_uniform.py:9: The name tf.random_uniform is deprecated. Please use tf.random.uniform instead.

W:tensorflow:From /home/toybrick/.local/lib/python3.7/site-packages/onnx_tf/handlers/backend/upsample.py:13: The name tf.image.resize_images is deprecated. Please use tf.image.resize instead.

/home/toybrick/.local/lib/python3.7/site-packages/onnx_tf/common/__init__.py:87: UserWarning: FrontendHandler.get_outputs_names is deprecated. It will be removed in future release.. Use node.outputs instead.
  warnings.warn(message)
W:tensorflow:From /home/toybrick/.local/lib/python3.7/site-packages/rknn/api/rknn.py:67: extract_sub_graph (from tensorflow.python.framework.graph_util_impl) is deprecated and will be removed in a future version.
Instructions for updating:
Use `tf.compat.v1.graph_util.extract_sub_graph`
E Catch exception when loading tensorflow model: tiny-yolo-voc.pb!
E Traceback (most recent call last):
E File "rknn/api/rknn_base.py", line 215, in rknn.api.rknn_base.RKNNBase.load_tensorflow
E File "rknn/base/RKNNlib/converter/convert_tf.py", line 527, in rknn.base.RKNNlib.converter.convert_tf.convert_tf.pre_process
E File "rknn/base/RKNNlib/converter/tensorflowloader.py", line 96, in rknn.base.RKNNlib.converter.tensorflowloader.TF_Graph_Preprocess.pre_proces
E File "rknn/base/RKNNlib/converter/tensorflowloader.py", line 555, in rknn.base.RKNNlib.converter.tensorflowloader.TF_Graph_Preprocess.import_tf_ruler_module
E File "/home/toybrick/.local/lib/python3.7/site-packages/rknn/base/RKNNlib/converter/tfruler/__init__.py", line 2, in <module>
E    from .tf_ruler_generate import r_add_n_template, r_concatv2_template, r_split_template
E ImportError: cannot import name 'r_add_n_template' from 'tfruler.tf_ruler_generate' (/home/toybrick/.local/lib/python3.7/site-packages/rknn/base/RKNNlib/converter/tfruler/tf_ruler_generate.cpython-37m-aarch64-linux-gnu.so)
done
--> Building model
Traceback (most recent call last):
  File "ex.py", line 32, in <module>
rknn.build(do_quantization=False)
  File "/home/toybrick/.local/lib/python3.7/site-packages/rknn/api/rknn.py", line 222, in build
inputs = self.rknn_base.net.get_input_layers()
AttributeError: 'NoneType' object has no attribute 'get_input_layers'

只看该作者 · 发表于 2020-5-20 10:54:09

E from .tf_ruler_generate import r_add_n_template, r_concatv2_template, r_split_template
E ImportError: cannot import name 'r_add_n_template' from 'tfruler.tf_ruler_generate' (/home/toybrick/.local/lib/python3.7/site-packages/rknn/base/RKNNlib/converter/tfruler/tf_ruler_generate.cpython-37m-aarch64-linux-gnu.so)

这个应该是某个op不支持