when I train,OpenCV error

[liujun0621]

first config:

Dataset Information

DATASET = "PH2_DeepLabV3_FT" IMAGES_DIR = "/home/user/Datasets/PH2Dataset/PH2_Segmented_Images_DLab_Trained_on_HAM10000" MASKS_DIR = "/home/user/Datasets/PH2Dataset/PH2_Masks_HAM10000"

second download： PH2: https://www.fc.up.pt/addi/ph2%20database.html

when run train, as follows: Traceback (most recent call last): File "/root/ccnn/coherent-cbe-skin-main/modeltraining.py", line 292, in , model_1 = engine.train(model=model, File "/root/ccnn/coherent-cbe-skin-main/modules/engine.py", line 262, in train train_loss, s_loss, c_loss, u_loss, concept_loss, train_acc = train_step(model=model, File "/root/ccnn/coherent-cbe-skin-main/modules/engine.py", line 72, in train_step for batch, data in enumerate(dataloader): File "/root/miniconda3/lib/python3.10/site-packages/torch/utils/data/dataloader.py", line 652, in next data = self._next_data() File "/root/miniconda3/lib/python3.10/site-packages/torch/utils/data/dataloader.py", line 1347, in _next_data return self._process_data(data) File "/root/miniconda3/lib/python3.10/site-packages/torch/utils/data/dataloader.py", line 1373, in _process_data data.reraise() File "/root/miniconda3/lib/python3.10/site-packages/torch/_utils.py", line 461, in reraise raise exception cv2.error: Caught error in DataLoader worker process 0. Original Traceback (most recent call last): File "/root/miniconda3/lib/python3.10/site-packages/torch/utils/data/_utils/worker.py", line 302, in _worker_loop data = fetcher.fetch(index) File "/root/miniconda3/lib/python3.10/site-packages/torch/utils/data/_utils/fetch.py", line 49, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/root/miniconda3/lib/python3.10/site-packages/torch/utils/data/_utils/fetch.py", line 49, in data = [self.dataset[idx] for idx in possibly_batched_index] File "/root/ccnn/coherent-cbe-skin-main/dataset.py", line 57, in getitem image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB) cv2.error: OpenCV(4.10.0) /io/opencv/modules/imgproc/src/color.cpp:196: error: (-215:Assertion failed) !_src.empty() in function 'cvtColor what problem could i take? what should i do next?

[liujun0621]

what is the relationship between data when we have downloaded from websit : https://www.fc.up.pt/addi/ph2%20database.html and "IMAGES_DIR = "/home/user/Datasets/PH2Dataset/PH2_Segmented_Images_DLab_Trained_on_HAM10000" MASKS_DIR = "/home/user/Datasets/PH2Dataset/PH2_Masks_HAM10000""

[CristianoPatricio]

Hi @liujun0621,

Thanks for your interest in our work. You need the masks from PH2 dataset. Please, send me an e-mail (cristiano.patricio@ubi.pt) so that I could share with you the masks and the preprocessed data.

[liujun0621]

ｔｈａｎｓｋｓ　ｖｅｒｙ　ｍｕｃｈ ｗｈｅｎ　ｉ　ｕｓｅ　ｔｒａｉｎｉｎｇ　ｒｅｓｕｌｔ　ｗｈｉｃｈ　ｉ　ｔｒａｉｎｅｄ ｔｈｅ　ｅｖａ　ａｓ　ｆｏｌｌｏｗｓ：

              2024-09-23 16:33:20

---

/////////// Dataset & Model Information ////////////

Dataset: PH2_DeepLabV3_FT_concept_loss_relu_tanh_0.6 Image Size: (765, 574) Image Type: Segmented (DeepLabV3 FT on HAM10000) Model: densenet201 Learning Rate: 0.001 No. Epochs: 100 Batch-Size: 16 /////////// Evaluation Report - Concepts ////////////

Exact Match Ratio: 0.0000 Hamming loss: 0.5050 Recall: 0.4571 Precision: 0.9480 F1 Measure: 0.6114

F1 Measure per Concept: [0.09 0.66 0.07 0.71 0.45 0.23 0.66 0.07] L2 distance: 10.04987562112089

/////////// Classification Report - Classes ////////////

Accuracy: 80.0000%

          precision    recall  f1-score   support

   Nevus       0.80      1.00      0.89        20
Melanoma       0.00      0.00      0.00         5

accuracy                           0.80        25

macro avg 0.40 0.50 0.44 25 weighted avg 0.64 0.80 0.71 25

Confusion Matrix: [[20 0] [ 5 0]] AUC: 0.5 Sensitivity: 0.0 Specificity: 1.0 BACC: 0.5

[liujun0621]

ｗｈｅｎ　ｉ　ｔｒａｉｎｅｄ，ｔｈｅｒｅ　ａｒｅ　ｎｏ　ｓａｖｅｍｏｄｅｌ　ｒｅｓｕｌｔ．