wudi00

ValueError: The passed save_path is not a valid checkpoint:

2

When I test the trained model, there is such error, why? Thanks `Traceback (most recent call last): File "./tools/test_net.py", line 113, in saver.restore(sess, args.model) File "/media/disk/wudi/.local/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1538, in restore...

train error

2

When I train my own datasets, there is such error: `Traceback (most recent call last): File "./tools/trainval_net.py", line 11, in from lib.model.train_val import get_training_roidb, train_net ModuleNotFoundError: No module named 'lib'`...

train VOC dataset

4

I train VOC dataset wit SSD 300, but loss is too high, why? I have modified the batchsize and learning rate. `iter 1680 || Loss: 1885.2950 || timer: 0.1291 sec....

` File "/media/disk/wudi/Faster-RCNN_TF-master/lib/fast_rcnn/test.py", line 6, in from lib.utils.cython_nms import nms, nms_new ModuleNotFoundError: No module named 'lib.utils.cython_nms'` when I run train_net.py there is such error, `No module named 'lib.utils.cython_nms'`, what can...

RuntimeError: cannot perform reduction function max on tensor with no elements because the operation does not have an identity

8

`Original Traceback (most recent call last): File "/media/disk/wudi/.local/lib/python3.6/site-packages/torch/utils/data/_utils/worker.py", line 178, in _worker_loop data = fetcher.fetch(index) File "/media/disk/wudi/.local/lib/python3.6/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/media/disk/wudi/.local/lib/python3.6/site-packages/torch/utils/data/_utils/fetch.py",...

python train.py

18

when I use `python train.py CenterNet-104` to train the model, there is such error `Traceback (most recent call last): File "train.py", line 43, in prefetch_data data, ind = sample_data(db, ind,...

train error

3

When I train on my own dataset there is such error `Traceback (most recent call last): File "train.py", line 231, in train(training_dbs, validation_db, args.start_iter) File "train.py", line 150, in train...

cuda10 train error

1

When I train on my own dataset there is such error - `RuntimeError: coalesce not supported on CUDAFloatType (coalesce at /pytorch/build/aten/src/ATen/CUDAFloatType.cpp:6232) frame #0: std::function::operator()() const + 0x11 (0x7f7ef5641021 in /media/disk/wudi/.local/lib/python3.6/site-packages/torch/lib/libc10.so)...

wrong with test

7

I used `python evaluate.py CornerNet_Saccade --testiter 500000 --split testing` to test coco datasets, but the result likes this: `Accumulating evaluation results... DONE (t=12.17s). Average Precision (AP) @[ IoU=0.50:0.95 | area=...

你好 训练自己的数据集时出现了这个错误， `TypeError: Failed to convert object of type to Tensor. Contents: [1, None]. Consider casting elements to a supported type.` 请问这是哪里的问题呢