2020-05-24 05:00:54 -0600 | commented answer | np.argmax returns 0 always Omg, you are right.. Im so happy thank you! |
2020-05-24 05:00:40 -0600 | received badge | ● Supporter (source) |
2020-05-24 05:00:39 -0600 | marked best answer | np.argmax returns 0 always To determine the class name of the detected object, I need to get the class_id of the image. The problem is, np.argmax always returns 0 and gets the first class name. When I detect another object, it should print class_id 1 but it prints 0 and I can't get the proper label name to display. When I look at my .txt files, I see this: 0 0.170103 0.449807 0.319588 0.521236 1 0.266791 0.148936 0.496269 0.287234 2 0.265464 0.422780 0.510309 0.420849 How I labeled my image: The result after training: In the result you can see that I dont see the label of the iphone and the rectangle is way above than I have selected. The airpods are also way bigger and samsung is at the bottom, which I didn't select like this. |
2020-05-24 05:00:39 -0600 | received badge | ● Scholar (source) |
2020-05-23 04:57:06 -0600 | commented answer | np.argmax returns 0 always Can you check my edit? |
2020-05-22 10:57:16 -0600 | edited answer | np.argmax returns 0 always @berak, I solved this problem. It was my fault, I did wrong string formatting when I started training it with darknet. I |
2020-05-22 10:50:44 -0600 | commented answer | np.argmax returns 0 always Check my edit |
2020-05-22 10:50:36 -0600 | edited question | np.argmax returns 0 always np.argmax returns 0 always To determine the class name of the detected object, I need to get the class_id of the image. |
2020-05-22 10:50:36 -0600 | received badge | ● Editor (source) |
2020-05-22 09:16:34 -0600 | commented question | np.argmax returns 0 always @berak, I solved this problem. It was my fault, I did wrong string formatting when I started training it with darknet. I |
2020-05-22 07:52:59 -0600 | received badge | ● Enthusiast |
2020-05-16 09:26:33 -0600 | commented question | np.argmax returns 0 always Yes, I have NMS included but I commented it out right now. |
2020-05-16 05:28:41 -0600 | commented question | np.argmax returns 0 always Any other idea maybe? |
2020-05-16 03:58:08 -0600 | commented question | np.argmax returns 0 always Yes, I trained my model on google colab for a few hours. When I had minimal loss, like 0.3 I stopped it with running. Wh |
2020-05-16 03:57:54 -0600 | commented question | np.argmax returns 0 always Yes, I trained my model on google colab for a few hours. When I had minimal loss, like 0.3 I stopped it with running. Wh |
2020-05-16 03:57:44 -0600 | commented question | np.argmax returns 0 always Yes, I trained my model on google colab for a few hours. When I had minimal loss, like 0.3 I stopped it with running. Wh |
2020-05-16 03:55:31 -0600 | commented question | np.argmax returns 0 always Yes, I trained my model on google colab for a few hours. When I had minimal loss, like 0.3 I stopped it with running. Wh |
2020-05-16 03:55:05 -0600 | commented question | np.argmax returns 0 always Yes, I trained my model on google colab for a few hours. When I had minimal loss, like 0.3 I stopped it with running. Wh |
2020-05-16 03:54:53 -0600 | commented question | np.argmax returns 0 always Yes, I trained my model on google colab for a few houres. When I had minimal loss, like 0.3 I stopped it with running. W |
2020-05-15 08:54:10 -0600 | asked a question | np.argmax returns 0 always np.argmax returns 0 always To determine the class name of the detected object, I need to get the class_id of the image. |