daliel

calibration to int8 INTERNAL ERROR: Assertion failed: d.nbDims >= 1

1

Tensorrt 7.0.0.11-1+cuda10.2 CUDA 10.2 Ubuntu 18.04 python3.6 torch 1.4.0 onnxruntime 1.1.1 code for calibration from: https://github.com/Tianxiaomo/pytorch-YOLOv4/issues/503 [TensorRT] ERROR: FAILED_EXECUTION: std::exception [TensorRT] WARNING: Explicit batch network detected and batch size specified,...

I wrote my env. my env returns: {'observ':np.ones((64,64,3),dtype=np.uint8)}, reward, done, info added to the tasks: ``` def own(config, params): # Works with `isolate_envs: thread`. action_repeat = params.get('action_repeat', 1) env_ctor =...

used docker conteiner: **nvcr.io/nvidia/tensorflow:19.10-py3** used script: **modfificated object_detection.py** for test created engine used trtexec in docker conteiner: ``` &&&& RUNNING TensorRT.trtexec # ./trtexec --loadEngine=/home/user/disc_brand/yolov3_INT8_1_segment0.trtengine --int8 [09/15/2020-17:13:02] [I] === Model Options...

my env: Ubuntu 18.04 cuda 10.2 cudnn 7.6.5 tensorrt 7.1.3 tensorrt oss libnvinfer_plugin.so.7.1.3 cudnn 7.6.5 installed from tar archive, CUDNN_INSTALL_DIR=/user/local/cuda onnx created with https://github.com/Tianxiaomo/pytorch-YOLOv4 in SampleYolo.cpp in bool SampleYolo::build() add...

calculating balance

1

I don't understand your math. my vision for calculating the balance is this: ``` if action == 2: # buy buy_order_size = order_size next_state.allocation_percentage = last_state.allocation_percentage + (1 - last_state.allocation_percentage)...