INPUT_SIZE = 160 if __name__ == '__main__': # Create RKNN object rknn = RKNN(verbose=True, verbose_file='./test2.log') #load rknn model print('--> Loading rknn model') rknn.load_rknn('./facenet_Reshape_1.rknn') print('done') #set inputs img1 = np.load(...
rknn_input_set, inputs[2].buf wrong, buf = 0x2909b790, size = 65536 (min_size = 262144...
sizeof(rknn_sdk_version)); printf("api version: %s\n", version.api_version); printf("driver version: %s\n", version.drv_version); 3.1.4 rknn_inputs_set API int rknn_inputs_set(rknn_context context, uint32_t n_inputs, rknn_input inputs[]) 功能 设置 inputs 的 buffer 以及参数....
示例代码如下: rknn_sdk_version version; ret = rknn_query(ctx, RKNN_QUERY_SDK_VERSION, &version, sizeof(rknn_sdk_version)); printf("sdk api version: %s\n", version.api_version); printf("driver version: %s\n", version.drv_version); 3.2.3.4 rknn_inputs_set 通过 rknn_inputs_set ...
逐层量化:以一个层为单位,整个layer的权重共用一组缩放因子 S 和偏移量 Z; 逐组量化:以组为单位,每个group使用一组 S 和 Z; 逐通道量化:以通道为单位,每个channel单独使用一组 S 和 Z。 当group = 1 时,逐组量化 = 逐层量化;当 group = num_filters(即 DW 卷积)时,逐组量化=逐通道量化。 5.3 ...
data = open('input.txt', 'r').read() # should be simple plain text file chars = list(set(data)) data_size, vocab_size = len(data), len(chars) print 'data has %d characters, %d unique.' % (data_size, vocab_size) char_to_ix = { ch:i for i,ch in enumerate(chars) } ...
param.num_npu_core = 2; param.top_k = 1; param.max_new_tokens = 256; param.max_context_len = 512; rkllm_init(&llmHandle, param, callback); printf("rkllm init success\n"); vector<string> pre_input; pre_input.push_back("把下面的现代文翻译成文言文:到了春风和煦,阳光明媚的时候,...
By company size Enterprises Small and medium teams Startups By use case DevSecOps DevOps CI/CD View all use cases By industry Healthcare Financial services Manufacturing Government View all industries View all solutions Resources Topics AI DevOps Security Software Development View all...
rknn_input inputs[]:输入数据数组,数组每个元素是 rknn_input 结构体对象。 返回值 int 错误码(见rknn 返回值错误码)。 示例代码如下: rknn_input inputs[1]; memset(inputs, 0, sizeof(inputs)); inputs[0].index = 0; inputs[0].type = RKNN_TENSOR_UINT8; inputs[0].size = img_width*img...
img = cv2.resize(img, (IMG_SIZE, IMG_SIZE)) # Inference outputs = rknn.inference(inputs=[img]) # post process input0_data = outputs[0] input1_data = outputs[1] input2_data = outputs[2] input0_data = input0_data.reshape([3, -1] + list(input0_data.shape[-2:])) ...