Hi, I met the eAI-501 error when I followed the guide of "3.5 How to create/save PyTorch model file" in the e-AI Translator V2.3.0 User's Manual.
Following is the log message.
"[2022-11-03 19:13:07,266 ERROR requirements.py:217 - log_exception() ] eAI-501 : Uncaught Exception An unhandled exception has caused this script to terminate prematurely. Here are the details :
Traceback (most recent call last):
File ".\bin\network_decoder.py", line 143, in <module>
File ".\bin\network_decoder.py", line 112, in generate_network
File ".\bin\error_code.py", line 37, in reraise
File ".\bin\network_decoder.py", line 104, in generate_network
File ".\bin\pytorch_dep\network_decoder_pytorch.py", line 157, in generate_network
ValueError: invalid literal for int() with base 10: ''
[2022-11-03 19:13:07,266 INFO requirements.py:218 - log_exception() ] Translation FAILED!![2022-11-03 19:13:07,266 INFO requirements.py:189 - remove_object() ] Uninitializing and cleaning up the translator object.."
I'm not sure what I missed. Could you check this error message and the used file (mnist.py)?
import torch import torch.nn as nn import torch.nn.functional as F class Net(nn.Module): def __init__(self): super(Net, self).__init__() self.conv1 = nn.Conv2d(1, 8, 3, padding=1) self.conv2 = nn.Conv2d(8, 16, 3, padding=1) self.dropout1 = nn.Dropout(0.25) self.dropout2 = nn.Dropout(0.5) self.fc1 = nn.Linear(784, 128) self.fc2 = nn.Linear(128, 10) def forward(self, x): x = self.conv1(x) x = F.relu(x) x = F.max_pool2d(x, 2) x = self.conv2(x) x = F.relu(x) x = F.max_pool2d(x, 2) x = self.dropout1(x) x = torch.flatten(x, 1) x = self.fc1(x) x = F.relu(x) x = self.dropout2(x) x = self.fc2(x) output = F.softmax(x, dim=1) return output
Hello.Today, I updated to the latest license file of e-AI translator (License_V230_20221130) according to the guide of 2.2 Copying the License File for the e-AI Translator in the e-AI Translator V2.3.0 User's Manual. After that, the PyTorch model has been successfully translated by the updated e-AI translator.
+---------------------------------+-----------------------+-----------------------+ | Layer Information | Size Information | Speed Information | +------------------+--------------+-----------+-----------+-----------------------+ | Layer Output No. | Layer Name | ROM(Byte) | RAM(Byte) | MAC Operations(times) | +------------------+--------------+-----------+-----------+-----------------------+ | 1 | Input | - | 3,136 | - | | | | | | | | 2 | Convolution | 320 | 28,688 | 56,448 | | | | | | | | 3 | ReLU | - | 25,088 | - | | | | | | | | 4 | Max Pooling | - | 6,272 | - | | | | | | | | 5 | Convolution | 4,672 | 20,736 | 225,792 | | | | | | | | 6 | ReLU | - | 12,544 | - | | | | | | | | 7 | Max Pooling | - | 3,136 | - | | | | | | | | 8 | Full Connect | 401,920 | 512 | 100,352 | | | | | | | | 9 | ReLU | - | 512 | - | | | | | | | | 10 | Full Connect | 5,160 | 40 | 1,280 | | | | | | | | 11 | Softmax | - | 40 | - | | | | | | | | 12 | Output | - | 40 | - | | | | | | | +------------------+--------------+-----------+-----------+-----------------------+ | | | | 100,744 | | | | TOTAL | 412,072 +-----------+ 383,872 | | | | | 40,808 | | +------------------+--------------+-----------+-----------+-----------------------+ # MAC : Multiply and ACcumulation(Number of product-sum operations) # Total RAM size (Upper) : Total size of All layers. # Total RAM size (Lower) : Actual size (Input + dnn_buffer1 + dnn_buffer2 + Output).
B.R.Y.H.Lee